© 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-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 110681
    Prev
    Next
    INDEX
    Explanations

    offensive languageor guideline violations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    …………..
    0.49
    蝓
    0.47
     ocasion
    0.45
     Calyce
    0.44
     Андроид
    0.43
     அமில
    0.42
    ………..
    0.42
     QUILL
    0.42
     Journ
    0.42
     ALLOYS
    0.42
    POSITIVE LOGITS
     potentially
    0.39
    ша
    0.38
     जिनका
    0.38
    ref
    0.38
     
    0.37
     مما
    0.36
    b
    0.36
     sadd
    0.36
    potentially
    0.35
    ис
    0.34
    Activations Density 0.001%

    No Known Activations