© 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. 65724
    Prev
    Next
    INDEX
    Explanations

    likely to be

    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
     végétal
    -1.10
     betrug
    -1.07
    tront
    -1.02
     florales
    -0.99
     that
    -0.97
     sév
    -0.97
     dentelle
    -0.95
    OOTDTY
    -0.94
     pép
    -0.93
    ₐ
    -0.93
    POSITIVE LOGITS
     can
    1.22
     able
    1.13
     likely
    1.06
     among
    1.05
     should
    1.04
     capable
    1.03
     unable
    1.00
     ought
    0.98
     comparable
    0.97
     Dateien
    0.97
    Activations Density 0.055%

    No Known Activations