© 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. 104410
    Prev
    Next
    INDEX
    Explanations

    how something is done

    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
     considerazione
    -1.10
     just
    -1.09
     scorso
    -1.05
    わかります
    -1.04
     didn
    -1.02
     because
    -1.02
    分かります
    -0.99
     from
    -0.98
     our
    -0.97
    лено
    -0.94
    POSITIVE LOGITS
     how
    2.09
     acceptable
    1.36
     expected
    1.27
     for
    1.21
     permissible
    1.19
     rules
    1.16
     allowable
    1.14
    ⿸
    1.12
    expected
    1.12
     hvordan
    1.11
    Activations Density 0.052%

    No Known Activations