© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 3861
    Prev
    Next
    INDEX
    Explanations

    option 3: short

    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
    ylar
    0.68
     dessus
    0.63
    ッコ
    0.62
     অধিকাংশ
    0.62
    kkal
    0.62
    readFileSync
    0.60
    詳
    0.60
    шем
    0.60
    +++
    0.60
    ద్ది
    0.59
    POSITIVE LOGITS
     Single
    0.79
     सिंगल
    0.78
    Single
    0.74
    简洁
    0.73
     masquer
    0.73
     Double
    0.73
     SINGLE
    0.72
     Landscape
    0.72
     layar
    0.71
     shortened
    0.71
    Activations Density 0.080%

    No Known Activations