© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47983
    Prev
    Next
    INDEX
    Explanations

    arguments and disagreements

    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_34/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
     maillot
    -1.09
    ἳ
    -1.07
     corollary
    -1.03
     Grenade
    -1.02
     obfer
    -1.01
    räume
    -0.98
    herent
    -0.95
     consom
    -0.95
    implies
    -0.94
     doctorate
    -0.94
    POSITIVE LOGITS
     cristianismo
    1.10
    liciter
    1.10
     kinds
    1.07
    Typically
    1.04
     instantiate
    0.96
     genuine
    0.95
     genuinely
    0.95
     Leiter
    0.93
     parecía
    0.92
     nennen
    0.92
    Activations Density 0.093%

    No Known Activations