© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91773
    Prev
    Next
    INDEX
    Explanations

    bio, synthetic, hydrophilic polymers

    np_acts-logits-general · gemini-2.5-flash-lite

    words and terms related to polymers and biomaterials in scientific contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is detecting chemical polymer–related terms (e.g. “poly-,” “polymer,” “polysaccharide,” “bio­polymer,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ريف
    -0.76
    וקה
    -0.70
    Votes
    -0.68
     NBC
    -0.67
     wages
    -0.67
     zpě
    -0.67
    แต
    -0.65
    pref
    -0.64
     تی
    -0.64
    provin
    -0.63
    POSITIVE LOGITS
     polymer
    4.84
     polymers
    4.59
     Polymer
    3.80
     polymeric
    3.80
    polymer
    3.59
    Polymer
    3.58
     Polymers
    3.56
     Polym
    2.83
     поли
    2.63
     polynomials
    2.58
    Activations Density 0.188%

    No Known Activations