© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14634
    Prev
    Next
    INDEX
    Explanations

    specific places and groups

    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
     someone
    -1.38
     somebody
    -1.29
     something
    -1.15
     überweisen
    -1.11
    itatea
    -1.10
    人の
    -1.06
     offrire
    -1.06
    heets
    -1.05
    "];
    -1.05
     fornire
    -1.03
    POSITIVE LOGITS
     who
    1.70
     are
    1.69
     have
    1.39
     should
    1.28
     will
    1.02
     Should
    1.01
    iteurs
    0.99
    who
    0.98
     Поэтому
    0.98
    jelent
    0.97
    Activations Density 0.086%

    No Known Activations