© 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-65K
    7. 5189
    Prev
    Next
    INDEX
    Explanations

    Old Man names

    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_65k_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
    shifted
    0.81
    좁
    0.70
    gü
    0.67
    ष्मा
    0.67
     lymphoblastic
    0.66
    Gw
    0.65
     shifted
    0.65
    $).
    0.64
     angiel
    0.64
    GMT
    0.63
    POSITIVE LOGITS
    ไม่ใช่
    0.70
    带领
    0.68
     इनके
    0.67
    ளர்
    0.66
    цца
    0.66
    وبي
    0.66
    oprotein
    0.65
     위해
    0.65
    linetype
    0.64
     yüz
    0.64
    Activations Density 0.001%

    No Known Activations