© 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. 129194
    Prev
    Next
    INDEX
    Explanations

    sports team matchups

    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
    ایب
    -0.90
    šné
    -0.89
    Ibid
    -0.88
     estos
    -0.86
    Melan
    -0.86
    Эти
    -0.85
     bolsos
    -0.84
     INCLUDING
    -0.84
    indro
    -0.82
    sibili
    -0.82
    POSITIVE LOGITS
     from
    1.00
    cho
    0.94
    针对
    0.88
    針對
    0.82
     睡
    0.78
    来自
    0.78
     objection
    0.76
    的问道
    0.76
    sepeda
    0.76
    onia
    0.74
    Activations Density 0.140%

    No Known Activations