© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 119036
    Prev
    Next
    INDEX
    Explanations

    licensed under

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     related
    -1.04
     of
    -0.91
     such
    -0.90
    不合
    -0.88
     aquest
    -0.87
    ;)
    -0.86
    aaS
    -0.85
     about
    -0.84
     CONSTITUTION
    -0.82
     until
    -0.82
    POSITIVE LOGITS
     rito
    0.98
    жает
    0.83
    排水
    0.82
     MessageType
    0.81
    Cá
    0.80
     misconceptions
    0.79
     uan
    0.79
    Acacia
    0.79
    bination
    0.77
    lüsse
    0.77
    Activations Density 0.001%

    No Known Activations