© 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. 17521
    Prev
    Next
    INDEX
    Explanations

    emoticons and punctuation

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

    refusal to offensive jokes

    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
    ​.
    0.42
    .​
    0.41
     Statewide
    0.40
    itur
    0.39
    NameValuePair
    0.39
    नांक
    0.38
    __.__
    0.38
    commodity
    0.38
     Neurology
    0.37
    POSITIVE LOGITS
    Navigation
    0.47
     Navigation
    0.46
     ---
    0.42
     navigation
    0.42
     NAVIGATION
    0.41
     ;
    0.40
    ---
    0.40
    Quote
    0.39
    NAVIGATION
    0.39
     pint
    0.38
    Activations Density 0.000%

    No Known Activations