© 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. 40-GEMMASCOPE-2-RES-262K
    7. 109685
    Prev
    Next
    INDEX
    Explanations

    specific text sequences after common words

    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
    市值
    0.41
     NÃO
    0.39
     唐
    0.38
     असंभव
    0.38
     wolves
    0.38
     treetops
    0.37
     tangle
    0.37
     tangled
    0.36
    নান
    0.36
    篮
    0.36
    POSITIVE LOGITS
    guid
    0.40
    uela
    0.39
    lective
    0.39
    ゾ
    0.38
     lesqu
    0.36
    闆
    0.36
    agi
    0.36
     Member
    0.36
     Lorraine
    0.36
    Guid
    0.35
    Activations Density 0.000%

    No Known Activations