© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 8337
    Prev
    Next
    INDEX
    Explanations

    list/array indexing

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

    accessing data by name or key

    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
     hastal
    0.33
     혹
    0.32
    뛰
    0.32
     अपन
    0.30
    vertebr
    0.30
    ދ
    0.30
    ᅳ
    0.30
    오
    0.29
    禪
    0.29
    ineau
    0.29
    POSITIVE LOGITS
    ._
    0.47
    "]["
    0.46
    ["
    0.45
    ']['
    0.45
    ()['
    0.45
    ->$
    0.42
    ['
    0.40
    ->_
    0.40
    ()["
    0.39
     psychologically
    0.37
    Activations Density 0.001%

    No Known Activations