© 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. 3076
    Prev
    Next
    INDEX
    Explanations

    probability and existence

    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
     bức
    -0.85
    nění
    -0.84
    öbb
    -0.83
    リュー
    -0.82
     relentless
    -0.82
    ⮕
    -0.80
     consistente
    -0.79
     insufic
    -0.79
     ferocious
    -0.78
     TVs
    -0.78
    POSITIVE LOGITS
     slim
    1.36
    slim
    1.31
     high
    1.30
     greater
    1.27
     increased
    1.23
     higher
    1.22
     exists
    1.21
     heightened
    1.14
     erhöhen
    1.08
    exist
    1.03
    Activations Density 0.033%

    No Known Activations