© 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. 7303
    Prev
    Next
    INDEX
    Explanations

    string manipulation and characters

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

    string methods

    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
     indexOf
    0.47
    indexOf
    0.42
    EventEmitter
    0.42
     Trim
    0.41
    托
    0.41
     trims
    0.41
    NoError
    0.40
    Tok
    0.39
     goc
    0.39
    Seattle
    0.39
    POSITIVE LOGITS
    strip
    1.02
    rstrip
    1.02
     strip
    1.00
    rjust
    0.92
    startswith
    0.89
    endswith
    0.89
    isdigit
    0.88
    isalpha
    0.88
     Strip
    0.81
    [::-
    0.79
    Activations Density 0.001%

    No Known Activations