© 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. 8049
    Prev
    Next
    INDEX
    Explanations

    parenthetical citations

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

    citations within parentheses

    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
    ;');
    0.48
     :}
    0.45
    ;(
    0.43
     ;\
    0.40
     ];
    0.39
     ؛
    0.39
     PDPN
    0.39
    ;')
    0.38
     -\
    0.38
     Ciò
    0.38
    POSITIVE LOGITS
    ate
    0.43
    kind
    0.43
    ｂ
    0.42
    ab
    0.41
    b
    0.41
    raise
    0.40
    aso
    0.40
    udent
    0.40
    unique
    0.39
    apt
    0.38
    Activations Density 0.015%

    No Known Activations