© 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. 73318
    Prev
    Next
    INDEX
    Explanations

    place finish scores

    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
     their
    -1.35
     already
    -1.30
     yesterday
    -1.12
     today
    -1.07
     recently
    -1.06
     new
    -1.06
     you
    -1.06
     сегодня
    -1.05
     now
    -1.04
     loro
    -1.03
    POSITIVE LOGITS
    bestimmungen
    1.23
    AGAIN
    1.23
     again
    1.19
    ɵɵelementEnd
    1.13
    ("")
    1.06
    ΅
    1.05
    gemeente
    1.03
     pañ
    1.02
    tranh
    1.02
     địch
    0.99
    Activations Density 0.003%

    No Known Activations