© 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. 72173
    Prev
    Next
    INDEX
    Explanations

    future predictions

    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
    儷
    -0.90
     быстро
    -0.89
    为您
    -0.89
     colocando
    -0.88
     zelfs
    -0.88
     bluzka
    -0.88
     spécialement
    -0.85
     eenvoudig
    -0.85
     dedicada
    -0.84
     hızlı
    -0.84
    POSITIVE LOGITS
     someday
    1.19
    Someday
    1.08
     improvements
    1.06
    改善
    1.04
     improvement
    1.04
     answers
    1.02
     better
    1.02
     improve
    0.94
     comprehensive
    0.92
     more
    0.90
    Activations Density 0.079%

    No Known Activations