© 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. 84762
    Prev
    Next
    INDEX
    Explanations

    watching television and streaming

    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
    肨
    0.51
    olées
    0.48
    iség
    0.46
     अगेन
    0.46
     аген
    0.46
    createdBy
    0.46
    徎
    0.46
    лізації
    0.45
    ída
    0.45
     Evanston
    0.45
    POSITIVE LOGITS
    including
    0.48
     Including
    0.47
     Mon
    0.45
     t
    0.44
     Purposes
    0.44
     vi
    0.43
     Modules
    0.43
     to
    0.41
     including
    0.41
    pur
    0.41
    Activations Density 0.000%

    No Known Activations