© 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. 47935
    Prev
    Next
    INDEX
    Explanations

    python import statements

    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
    äjä
    -0.84
    犷
    -0.78
     мають
    -0.78
    ɨ
    -0.76
     està
    -0.75
    ออก
    -0.74
     realised
    -0.74
     zů
    -0.73
     to
    -0.72
     familiar
    -0.72
    POSITIVE LOGITS
    NOC
    1.19
    NIS
    1.05
    from
    0.98
     vannak
    0.90
    美しく
    0.88
     thence
    0.87
     NOC
    0.87
    ˿
    0.87
     ①
    0.87
     thunk
    0.86
    Activations Density 0.007%

    No Known Activations