© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77660
    Prev
    Next
    INDEX
    Explanations

    Java programming constructs

    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
     démar
    -0.91
    修
    -0.88
    Pins
    -0.86
    －
    -0.85
     vedere
    -0.84
     hü
    -0.82
    Milton
    -0.81
    Anne
    -0.79
    ∕
    -0.79
    Фран
    -0.78
    POSITIVE LOGITS
     flasks
    0.85
    يكا
    0.82
    馊
    0.79
     verbessern
    0.77
    FTS
    0.75
     entsprechend
    0.74
    呛
    0.74
    ctus
    0.73
    事実
    0.73
    cutta
    0.73
    Activations Density 0.026%

    No Known Activations