© 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. 110582
    Prev
    Next
    INDEX
    Explanations

    i followed by number, _ followed by precision

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

    underscores followed by digits in variable names or identifiers in code.

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

    The neuron fires on numeric literals (tokens composed of digits, with or without decimal point) such as integer or floating-point constants.

    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
     erwähnten
    -1.41
    祆
    -1.35
    =#{
    -1.33
     a
    -1.30
    ”，
    -1.30
     pintadas
    -1.24
     Kühlschrank
    -1.24
     católica
    -1.24
    zość
    -1.23
    ()}
    -1.20
    POSITIVE LOGITS
    しなかった
    1.47
     этого
    1.45
     этой
    1.41
    일본
    1.39
     this
    1.38
     сюда
    1.38
     Parenthood
    1.33
     또는
    1.33
    德國
    1.29
     dernière
    1.28
    Activations Density 0.006%

    No Known Activations