© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 75017
    Prev
    Next
    INDEX
    Explanations

    end of preview or new entries

    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
    providedIn
    -1.30
     (
    -1.12
    centerTitle
    -1.05
    лось
    -1.03
    phrodite
    -1.02
    ￭
    -1.00
    requipa
    -0.99
    ÑO
    -0.97
    izm
    -0.96
    complish
    -0.94
    POSITIVE LOGITS
    9
    1.52
    4
    1.48
    6
    1.48
    8
    1.38
    3
    1.35
    5
    1.34
    7
    1.20
    مشخص
    1.14
    最後まで
    1.09
    چنین
    1.08
    Activations Density 0.000%

    No Known Activations