© 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. 31-GEMMASCOPE-2-RES-262K
    7. 125329
    Prev
    Next
    INDEX
    Explanations

    muffled speech 'mmph'

    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_31_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
    ಂಕ್
    0.50
    یسر
    0.50
    桫
    0.48
    produk
    0.48
    瘙
    0.46
     residuos
    0.45
    鴟
    0.45
    ஷ்
    0.45
     auxilia
    0.45
    ீரி
    0.45
    POSITIVE LOGITS
     confirmation
    0.57
     midnight
    0.54
     cruising
    0.52
     I
    0.51
    /
    0.48
     PASS
    0.46
     determination
    0.46
     like
    0.44
     confirm
    0.44
     still
    0.44
    Activations Density 0.009%

    No Known Activations