© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 79598
    Prev
    Next
    INDEX
    Explanations

    sports scores and records

    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
     ゲ
    -0.89
    Worst
    -0.88
     Renov
    -0.84
     Tole
    -0.83
    После
    -0.82
     Loa
    -0.82
     recommandé
    -0.81
     cemento
    -0.80
    ماش
    -0.79
     kommet
    -0.79
    POSITIVE LOGITS
    primaryColor
    0.85
     electric
    0.81
     hardened
    0.80
    ➞
    0.78
    (!_
    0.77
    疱
    0.75
     more
    0.75
    整天
    0.75
     kemarin
    0.73
    posium
    0.73
    Activations Density 0.026%

    No Known Activations