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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108135
    Prev
    Next
    INDEX
    Explanations

    origins and meanings of words

    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
    Nearby
    -0.93
    紂
    -0.86
     actualité
    -0.85
    createNew
    -0.82
    ,%
    -0.82
    その時
    -0.81
    rolment
    -0.77
    годно
    -0.77
    事前に
    -0.76
     تصمیم
    -0.75
    POSITIVE LOGITS
     earliest
    1.00
     later
    0.99
     earlier
    0.97
     attested
    0.97
     related
    0.96
     from
    0.93
     diretamente
    0.92
    ODO
    0.91
     early
    0.86
    用例
    0.84
    Activations Density 0.046%

    No Known Activations