© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 2379
    Prev
    Next
    INDEX
    Explanations

    list items

    np_acts-logits-general · gemini-2.5-flash-lite

    frost on the ground

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Namun
    0.25
    '،
    0.25
    Asimismo
    0.25
    '=>
    0.25
     diese
    0.24
     dieser
    0.23
     beispielsweise
    0.23
    $,
    0.23
     fins
    0.23
    "،
    0.23
    POSITIVE LOGITS
     Various
    0.46
     Other
    0.42
     Multiple
    0.41
     Identifying
    0.41
     Перейти
    0.40
     Diverse
    0.39
     Additional
    0.39
     Increasing
    0.38
     Different
    0.38
     Several
    0.38
    Activations Density 0.736%

    No Known Activations