© 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. 2327
    Prev
    Next
    INDEX
    Explanations

    the plus names or descriptions

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

    refusals by Gemma team

    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
     `${
    0.47
     BOTH
    0.46
     certa
    0.43
     olev
    0.42
     sepd
    0.41
     england
    0.40
     certains
    0.40
     wt
    0.40
     (`
    0.40
     Includes
    0.40
    POSITIVE LOGITS
     eponymous
    0.82
     titular
    0.58
     aforementioned
    0.54
     namesake
    0.52
     eponym
    0.50
     entirety
    0.49
     aptly
    0.46
     erstwhile
    0.44
    mselves
    0.43
     secretive
    0.43
    Activations Density 0.037%

    No Known Activations