© 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. 72304
    Prev
    Next
    INDEX
    Explanations

    code syntax like @ and comments

    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
    餡
    -1.07
    もしか
    -1.06
     by
    -1.04
    調味料
    -1.03
     despite
    -0.99
     last
    -0.95
    ASC
    -0.94
     change
    -0.94
    fowl
    -0.93
    brite
    -0.93
    POSITIVE LOGITS
     květ
    1.15
     and
    1.09
     néanmoins
    1.06
     razu
    1.05
     aviones
    1.05
     dáms
    1.05
     nervios
    1.04
     zimní
    1.04
     extremadamente
    1.02
     perfectamente
    1.00
    Activations Density 0.009%

    No Known Activations