© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 149415
    Prev
    Next
    INDEX
    Explanations

    casinos

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
    িয়ের
    0.79
    英国
    0.79
     wissen
    0.74
    癶
    0.74
    យ៉ាង
    0.74
     avrà
    0.73
     Жен
    0.73
    десят
    0.73
    Ꮶ
    0.73
     क्वेश्च
    0.72
    POSITIVE LOGITS
    வல
    0.77
     reverse
    0.68
     swamp
    0.67
     plug
    0.66
     SBS
    0.65
     clauses
    0.64
     shy
    0.63
    જબ
    0.62
     kangaroo
    0.62
     april
    0.62
    Activations Density 0.000%

    No Known Activations