© 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. 70573
    Prev
    Next
    INDEX
    Explanations

    disorder, people, development

    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
     their
    -1.38
     with
    -1.21
    DialogInterface
    -1.08
     its
    -1.07
    armani
    -1.06
     серебри
    -1.05
     on
    -1.05
     by
    -1.03
     diverse
    -1.02
     it
    -1.01
    POSITIVE LOGITS
    整个人
    1.20
     weihnachten
    1.16
    ,..
    1.16
     protože
    1.13
    ,;
    1.12
    artigen
    1.07
    minator
    1.06
    ;,
    1.04
    ..,
    1.03
     présentent
    1.02
    Activations Density 0.000%

    No Known Activations