© 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. 15956
    Prev
    Next
    INDEX
    Explanations

    most of the

    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
     sometimes
    -1.95
     and
    -1.66
     particularly
    -1.59
     may
    -1.55
     possibly
    -1.55
     as
    -1.52
     many
    -1.50
     some
    -1.50
     might
    -1.48
     different
    -1.47
    POSITIVE LOGITS
    Either
    1.55
     большин
    1.54
     большинстве
    1.23
    Except
    1.23
    either
    1.20
     Meksiko
    1.19
     современных
    1.19
    licopter
    1.17
    generally
    1.13
     只
    1.11
    Activations Density 0.086%

    No Known Activations