© 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. 66095
    Prev
    Next
    INDEX
    Explanations

    official events and decisions

    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
    εις
    -1.07
     from
    -1.06
    under
    -1.05
    ͦ
    -1.03
     UNF
    -0.96
    andes
    -0.95
    chaikovsky
    -0.95
     ibid
    -0.95
     ABOVE
    -0.93
     bourse
    -0.92
    POSITIVE LOGITS
     antidesliz
    1.14
    upcoming
    1.10
    に行ってきました
    1.09
     trajo
    1.06
     confirmó
    1.05
     everyone
    1.04
    Pró
    1.02
     recargable
    1.01
     десер
    0.97
     will
    0.96
    Activations Density 0.141%

    No Known Activations