© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101626
    Prev
    Next
    INDEX
    Explanations

    /* Callbacks for FSM

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

    the digit zero in technical or programming contexts, particularly in numerical data, code, or structured formats.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on numeric literal tokens (decimal or integer constants) in the text.

    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
     which
    -1.66
     by
    -1.38
    -1.38
     to
    -1.35
    -1.34
     whom
    -1.30
     whose
    -1.30
     не
    -1.24
     either
    -1.23
    뿍
    -1.23
    POSITIVE LOGITS
    ぞれ
    1.47
    Vaya
    1.43
     fuir
    1.42
    白色的
    1.38
    𝔗
    1.38
     diamants
    1.36
     recev
    1.35
     tatou
    1.33
     materie
    1.32
    嗞
    1.31
    Activations Density 0.033%

    No Known Activations