© 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-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 34184
    Prev
    Next
    INDEX
    Explanations

    Glitch Tokens

    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_53_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
     Offences
    0.41
     REPUBLIC
    0.37
    嚓
    0.37
    પ્
    0.37
    igable
    0.36
    हिमा
    0.36
     Repubblica
    0.36
     кола
    0.36
    벳
    0.36
     ब्रा
    0.35
    POSITIVE LOGITS
    άλ
    0.42
     Leistung
    0.42
     বেগ
    0.41
    ಲ್ಲ
    0.39
     unincorporated
    0.39
    '"
    0.37
    શ્ર
    0.37
    '",
    0.36
    formul
    0.36
    liquidacion
    0.36
    Activations Density 0.002%

    No Known Activations