© 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. 60476
    Prev
    Next
    INDEX
    Explanations

    native technology and success

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

    The neuron specifically detects the numeric token “4,” as it appears (e.g. in line-number references).

    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
    //=
    -0.85
     FileReader
    -0.82
     другие
    -0.82
     pronunci
    -0.79
     GetEnumerator
    -0.79
     HttpContext
    -0.78
    🅰
    -0.78
    altri
    -0.78
    НК
    -0.77
     стола
    -0.77
    POSITIVE LOGITS
    τρο
    0.99
    successful
    0.92
     التاريخ
    0.89
     successful
    0.83
     Successful
    0.83
    ه‌ی
    0.83
     Faithful
    0.79
    hObject
    0.78
     exitos
    0.77
    Hechos
    0.76
    Activations Density 0.001%

    No Known Activations