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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 582
    Prev
    Next
    INDEX
    Explanations

    Maven groupId definitions

    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_10/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
    '
    -2.86
     Hinblick
    -2.73
    gencias
    -2.56
    ")))
    -2.48
    ghalaya
    -2.45
    肯定是
    -2.41
     gewähr
    -2.38
    鹗
    -2.36
     When
    -2.34
    “
    -2.34
    POSITIVE LOGITS
    on
    3.03
     города
    2.33
    ">
    2.33
    ERS
    2.25
     entirety
    2.17
    but
    2.11
    </h4>
    2.05
    CommonModule
    2.05
    providedIn
    2.03
     carpenter
    2.02
    Activations Density 0.069%

    No Known Activations