© 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. 25881
    Prev
    Next
    INDEX
    Explanations

    risk factors, call of duty, personality, code comments

    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
    greja
    -1.16
    ihnachts
    -1.11
    denly
    -1.01
    álna
    -0.99
     fiasco
    -0.99
    .~\
    -0.98
     séjours
    -0.98
     niem
    -0.98
    ⚌
    -0.97
     Franse
    -0.97
    POSITIVE LOGITS
     because
    1.02
     with
    0.92
     on
    0.90
    According
    0.89
     had
    0.89
     remained
    0.88
     not
    0.88
     completely
    0.86
     metter
    0.85
    Following
    0.84
    Activations Density 0.000%

    No Known Activations