© 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. 34-GEMMASCOPE-RES-131K
    7. 82447
    Prev
    Next
    INDEX
    Explanations

    programming or technical terms

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

    The neuron activates on numeric literals (sequences of digits) 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_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
    ";//
    -1.03
    ?;
    -1.02
     misschien
    -0.93
    ()))
    -0.90
     "";
    -0.90
     unless
    -0.90
    }$;
    -0.89
    ”;
    -0.88
     terjangkau
    -0.87
     ();
    -0.85
    POSITIVE LOGITS
    تو
    0.86
    digde
    0.85
    andidate
    0.81
     commandement
    0.79
    อะ
    0.77
    权
    0.77
     допо
    0.75
    ًا
    0.75
     تز
    0.75
    SizedBox
    0.74
    Activations Density 0.000%

    No Known Activations