© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38287
    Prev
    Next
    INDEX
    Explanations

    personalized and relevant advertisements

    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
    strtotime
    -1.15
    торами
    -1.11
     ilust
    -1.11
     необходимости
    -1.09
     robuste
    -1.07
    ENERGY
    -1.06
     violen
    -1.05
     accepte
    -1.04
     pecu
    -1.03
     curios
    -1.03
    POSITIVE LOGITS
     based
    1.86
     your
    1.34
     goûts
    1.16
    based
    1.16
     personnaliser
    1.15
     information
    1.14
     only
    1.14
     alapján
    1.12
     personalized
    1.09
    Based
    1.08
    Activations Density 0.037%

    No Known Activations