© 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. 67262
    Prev
    Next
    INDEX
    Explanations

    variable declarations

    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
    вгений
    -1.13
    Depending
    -1.09
    Been
    -1.06
    Again
    -1.05
    あっという間に
    -1.03
    ‰
    -1.03
    poptotic
    -1.02
    Whether
    -1.01
     необходимости
    -1.01
    いよいよ
    -1.00
    POSITIVE LOGITS
     even
    1.28
     a
    1.27
     test
    1.23
     after
    1.18
     result
    1.17
     an
    1.13
     some
    1.12
     results
    1.09
     expect
    1.08
     another
    1.03
    Activations Density 0.014%

    No Known Activations