© 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. 26718
    Prev
    Next
    INDEX
    Explanations

    states, conditions, or requirements

    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
     Endlich
    -1.14
    又被
    -1.13
     respecting
    -1.09
     cotidiana
    -1.08
     هیچ
    -1.08
     SHOES
    -1.08
    ategories
    -1.07
    リーツ
    -1.04
     ModelRenderer
    -1.04
    venirs
    -1.03
    POSITIVE LOGITS
    ibility
    1.40
    </h4>
    1.38
    atized
    1.37
    ensitive
    1.36
    ments
    1.34
    atical
    1.32
    alties
    1.30
    ogues
    1.29
    ignment
    1.27
    vereignty
    1.27
    Activations Density 0.117%

    No Known Activations