© 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. 4858
    Prev
    Next
    INDEX
    Explanations

    units and separators

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

    variables or short sequences

    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
    或其他
    0.48
    及其
    0.45
    并通过
    0.42
    并在
    0.40
    和其他
    0.38
    并
    0.38
    HEN
    0.36
    Հ
    0.35
    ({'
    0.35
    াল
    0.35
    POSITIVE LOGITS
     ::
    0.43
     |
    0.41
    ாகவும்
    0.41
     ხოლო
    0.39
     就是
    0.38
     cierra
    0.38
    dit
    0.36
     \|
    0.36
     ---------
    0.36
    jsdel
    0.36
    Activations Density 0.070%

    No Known Activations