© 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. 22-GEMMASCOPE-RES-131K
    7. 73272
    Prev
    Next
    INDEX
    Explanations

    various outcomes

    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_22/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
     conferencia
    -1.03
     even
    -1.02
     this
    -0.99
     while
    -0.96
    ماه
    -0.90
     cuadrada
    -0.90
     totalmente
    -0.88
     but
    -0.88
    lagem
    -0.86
     just
    -0.86
    POSITIVE LOGITS
     various
    1.68
     other
    1.59
     berbagai
    1.55
     các
    1.54
     여러
    1.48
     विभिन्न
    1.43
    various
    1.42
    several
    1.42
     certain
    1.38
     VARIOUS
    1.38
    Activations Density 0.207%

    No Known Activations