© 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. 22-GEMMASCOPE-RES-131K
    7. 36637
    Prev
    Next
    INDEX
    Explanations

    web file paths and extensions

    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
    ;
    -1.24
    続
    -1.13
    <i>
    -1.11
     though
    -1.10
    }$
    -1.09
     notwithstanding
    -1.09
    WHEN
    -1.08
    loride
    -1.08
    ribune
    -1.04
     nachdem
    -1.04
    POSITIVE LOGITS
     disiplin
    1.27
     \'
    1.13
     meil
    1.12
    皤
    1.12
     diki
    1.11
     reporta
    1.10
     FILLER
    1.09
    postolic
    1.09
     cubana
    1.08
     puse
    1.07
    Activations Density 0.015%

    No Known Activations