© 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. 26656
    Prev
    Next
    INDEX
    Explanations

    package identifiers or URLs

    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
     muualla
    -1.23
    MessageDigest
    -1.16
     bereits
    -1.14
    芣
    -1.13
    Cuánt
    -1.13
     inici
    -1.13
    </tfoot>
    -1.11
    kres
    -1.07
     balón
    -1.07
     will
    -1.07
    POSITIVE LOGITS
    と思って
    1.21
    があるので
    1.16
    がありますが
    1.11
     flach
    1.10
    參見
    1.08
    Biblia
    1.08
    although
    1.07
     remplacer
    1.05
    especially
    1.05
    詢
    1.05
    Activations Density 0.000%

    No Known Activations