© 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. 129117
    Prev
    Next
    INDEX
    Explanations

    code delimiters and numbers

    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
     zaczą
    -0.93
     mógł
    -0.89
    ڑ
    -0.88
     caneta
    -0.87
     députés
    -0.85
    kac
    -0.82
     hoist
    -0.81
     sypial
    -0.80
     journalistes
    -0.78
    以來
    -0.78
    POSITIVE LOGITS
     števil
    0.92
    dev
    0.88
     to
    0.87
     Zone
    0.85
    tispiece
    0.82
     Mod
    0.79
    ")));
    0.79
    페
    0.79
     Ö
    0.78
    ANY
    0.78
    Activations Density 0.168%

    No Known Activations