© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8179
    Prev
    Next
    INDEX
    Explanations

    interfaces or biology

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

    words related to "invertebrates" or biological terminology about small organisms.

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

    The neuron strongly activates on tokens referring to “vertebrate”-type words (e.g. vertebrates, invertebrate, invertebrates).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     einigen
    -2.28
     kleinen
    -2.27
     selben
    -2.14
    y
    -2.11
     neuen
    -2.09
     vorigen
    -2.05
    e
    -2.05
    it
    -2.05
     einer
    -1.99
    h
    -1.99
    POSITIVE LOGITS
     was
    2.48
    你们的
    2.25
     dizzy
    2.23
    彼が
    2.23
    甞
    2.00
    는
    1.97
    interfaces
    1.95
    我还是
    1.92
     می‌شود
    1.91
    旁邊
    1.91
    Activations Density 0.006%

    No Known Activations