© 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. 22-GEMMASCOPE-RES-131K
    7. 12382
    Prev
    Next
    INDEX
    Explanations

    causal relationship

    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
    InjectAttribute
    -1.10
    struzioni
    -1.08
    TagHelpers
    -1.06
     Semantics
    -1.06
    inerary
    -1.05
    nadequate
    -1.04
    ığını
    -1.03
    PostInfinity
    -1.03
     müßte
    -1.02
     chyb
    -1.01
    POSITIVE LOGITS
     also
    1.59
    Also
    1.12
    e
    1.09
    re
    1.06
     namanya
    1.02
    b
    0.99
    s
    0.99
    a
    0.98
     isn
    0.98
     dessutom
    0.97
    Activations Density 0.045%

    No Known Activations