Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11653
    Prev
    Next
    INDEX
    Explanations

    Star Awards

    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_22/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
    还需要
    -0.93
     also
    -0.93
    还要
    -0.92
     grund
    -0.91
    也不能
    -0.89
    Warmly
    -0.89
     vissa
    -0.88
    还可以
    -0.88
    観音
    -0.88
     lar
    -0.87
    POSITIVE LOGITS
    Ży
    0.91
     chose
    0.88
     ステーキ
    0.87
    Quaternion
    0.86
    izacji
    0.84
    lottesville
    0.84
    漢
    0.82
    choice
    0.81
    roaches
    0.81
     scegliere
    0.81
    Activations Density 0.003%

    No Known Activations