© 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. 65795
    Prev
    Next
    INDEX
    Explanations

    list prices

    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
     arşivlendi
    -1.02
     picha
    -0.91
    ޑ
    -0.89
     rimane
    -0.85
     asam
    -0.85
     reconnaître
    -0.84
     かわいい
    -0.84
     publier
    -0.83
     exprimer
    -0.82
    bereiche
    -0.81
    POSITIVE LOGITS
     (
    2.23
     although
    1.54
     which
    1.53
     but
    1.41
     Although
    1.34
    although
    1.21
     aunque
    1.21
    Aunque
    1.13
    ※
    1.09
     Aunque
    1.07
    Activations Density 0.200%

    No Known Activations