© 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. 128381
    Prev
    Next
    INDEX
    Explanations

    base class structure

    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
     envies
    -1.15
     komplet
    -1.11
     faç
    -1.11
     alho
    -1.07
     verschillende
    -1.07
    mäs
    -1.05
     💕
    -1.05
    динг
    -1.05
     rues
    -1.04
     attaché
    -1.04
    POSITIVE LOGITS
     with
    1.31
     where
    1.19
     should
    1.17
     at
    1.13
     Despite
    1.09
     despite
    1.08
     does
    1.08
     although
    1.07
     Because
    1.07
     came
    1.06
    Activations Density 0.006%

    No Known Activations