© 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. 11430
    Prev
    Next
    INDEX
    Explanations

    validation and checking

    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
     尺寸
    -1.17
     bugün
    -1.16
    殡
    -1.13
    *-*-
    -1.09
     手順
    -1.08
     hiçbir
    -1.05
     ubica
    -1.05
    ország
    -1.05
     vítimas
    -1.05
     garam
    -1.04
    POSITIVE LOGITS
     check
    1.44
     checking
    1.34
     testing
    1.30
     test
    1.24
     applied
    1.21
     preventing
    1.16
     apply
    1.16
     you
    1.14
     prevent
    1.14
     sensitivity
    1.10
    Activations Density 0.036%

    No Known Activations