© 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. 108435
    Prev
    Next
    INDEX
    Explanations

    avoiding major spoilers

    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
    <0x8A>
    0.43
    hesize
    0.42
    rothed
    0.41
    fledged
    0.41
    енера
    0.41
    ти
    0.40
    ppel
    0.40
    osion
    0.40
    тил
    0.39
    டையே
    0.39
    POSITIVE LOGITS
     해
    0.46
    कोड
    0.46
     poem
    0.46
     ni
    0.45
     poems
    0.45
     नेता
    0.45
     çat
    0.45
    ویان
    0.44
     köl
    0.44
    ဂ
    0.43
    Activations Density 0.001%

    No Known Activations