© 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. 10-GEMMASCOPE-RES-131K
    7. 67946
    Prev
    Next
    INDEX
    Explanations

    provided "as is"

    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_10/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
     of
    -2.20
     from
    -1.45
    borderSide
    -1.33
    𝟐
    -1.32
     via
    -1.32
     on
    -1.32
    unduh
    -1.30
    avras
    -1.30
    anwal
    -1.30
     Its
    -1.29
    POSITIVE LOGITS
     первого
    1.50
     biraz
    1.49
    ↵
    1.48
     there
    1.43
     primeras
    1.43
     несколь
    1.41
     sometime
    1.41
     it
    1.34
     некоторы
    1.34
     semillas
    1.32
    Activations Density 0.043%

    No Known Activations