© 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. 15480
    Prev
    Next
    INDEX
    Explanations

    make a purchase

    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
     alimentazione
    -1.23
    🤚
    -1.19
    狍
    -1.14
     länder
    -1.06
     Muzeum
    -1.05
     can
    -1.05
     hoffe
    -1.04
     of
    -1.02
     rác
    -1.01
     always
    -1.00
    POSITIVE LOGITS
     adjustments
    1.19
     Perhaps
    1.16
    おもしろ
    1.07
    šené
    1.07
     amends
    1.05
     стоимости
    1.04
    他对
    1.04
     strides
    1.03
    Perhaps
    1.03
     Of
    1.02
    Activations Density 0.079%

    No Known Activations