© 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. 93618
    Prev
    Next
    INDEX
    Explanations

    permissions, subscription, information, data

    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
    anias
    -0.87
     inference
    -0.86
     Flows
    -0.82
     romero
    -0.79
     Gewebe
    -0.77
    ⅜
    -0.75
     Komponenten
    -0.75
    лке
    -0.75
     fhew
    -0.74
    гро
    -0.73
    POSITIVE LOGITS
     reprints
    0.86
    Email
    0.81
    ="@+
    0.79
    Reprints
    0.79
    Mann
    0.78
     permission
    0.78
    Rispondi
    0.76
    JHEP
    0.76
    iconque
    0.75
    Permission
    0.74
    Activations Density 0.051%

    No Known Activations