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. 34-GEMMASCOPE-RES-131K
    4. 109965
    Prev
    Next
    INDEX
    Explanations

    rules and requirements

    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
     your
    -1.03
     것입니다
    -0.92
    Btw
    -0.91
    Interventions
    -0.91
     Ön
    -0.90
    不了
    -0.87
     you
    -0.86
     beautiful
    -0.85
     really
    -0.85
    ',\
    -0.81
    POSITIVE LOGITS
     SHOULD
    1.81
    MUST
    1.47
     SHALL
    1.47
     RECOMMENDED
    1.31
    MAY
    1.29
     MUST
    1.29
     MAY
    1.21
    IANA
    1.19
    SHO
    1.18
    haling
    1.14
    Activations Density 0.091%

    No Known Activations