© 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. 7583
    Prev
    Next
    INDEX
    Explanations

    enumerated list items

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

    start of numbered list item

    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
    .___
    0.46
    .__
    0.42
     delimit
    0.42
    
    0.39
    fi
    0.38
    ._
    0.38
     close
    0.38
     scarcely
    0.38
    .’’
    0.37
    kV
    0.37
    POSITIVE LOGITS
     sourire
    0.44
    ométrique
    0.42
    Ironically
    0.41
    Numero
    0.41
    BigDecimal
    0.41
    亢
    0.41
    ყო
    0.39
     MOST
    0.39
    時間が
    0.38
    laublich
    0.38
    Activations Density 0.017%

    No Known Activations