© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77574
    Prev
    Next
    INDEX
    Explanations

    technical or user input contexts

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

    The neuron fires on sequences of numeric characters (digits and punctuation like dots), i.e. number or version‐number patterns.

    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
    קישורים
    -0.93
     what
    -0.89
    dateTime
    -0.81
     delivers
    -0.79
    DateTime
    -0.79
     mostly
    -0.79
     always
    -0.77
     concessions
    -0.75
    GMENT
    -0.75
    備考
    -0.75
    POSITIVE LOGITS
    吸収
    0.85
    付近
    0.81
    inin
    0.79
    beginning
    0.77
     unn
    0.76
     CLA
    0.76
     donnant
    0.75
     EXPLANATION
    0.74
    ք
    0.74
    篭
    0.73
    Activations Density 0.009%

    No Known Activations