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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 71003
    Prev
    Next
    INDEX
    Explanations

    startswith name or chemical prefixes

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

    the neuron activates for technical terms, product names, and specialized terminology, particularly in scientific and technical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     all
    -1.38
     but
    -1.36
    <bos>
    -1.20
    kimono
    -1.12
    crity
    -1.09
     two
    -1.07
     those
    -1.07
    しません
    -1.06
    ல்ல
    -1.03
    onOptions
    -1.03
    POSITIVE LOGITS
     urat
    1.27
    넬
    1.14
     chaus
    1.14
     achat
    1.04
     abonnement
    1.02
     digitale
    1.01
     bombe
    0.99
    為に
    0.99
    your
    0.98
     dezelve
    0.98
    Activations Density 0.050%

    No Known Activations