© 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. 26950
    Prev
    Next
    INDEX
    Explanations

    Filed, Thank, It

    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
     timpul
    -0.99
     siis
    -0.93
    sivité
    -0.92
    ENTO
    -0.91
    祝い
    -0.90
    enterOuterAlt
    -0.90
     خدمات
    -0.89
     necesitar
    -0.88
    boxylic
    -0.88
     inhoud
    -0.88
    POSITIVE LOGITS
     another
    1.05
     Posteriormente
    0.93
     laiton
    0.89
    ąć
    0.87
    ǿ
    0.84
     השני
    0.83
    Embal
    0.82
    тни
    0.82
     selam
    0.82
    лни
    0.82
    Activations Density 0.004%

    No Known Activations