© 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-262K
    7. 147780
    Prev
    Next
    INDEX
    Explanations

    social history

    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
    ্ঞ
    0.71
     ძალი
    0.70
    覃
    0.69
    raquinone
    0.69
    丁寧
    0.68
     intensify
    0.66
    炔
    0.66
     cautioned
    0.66
    謦
    0.66
    жити
    0.66
    POSITIVE LOGITS
     Represents
    0.78
     Represent
    0.78
     Representation
    0.76
     unimportant
    0.73
    headed
    0.69
     Held
    0.68
     representa
    0.67
     खेळा
    0.65
     Representations
    0.65
     Enter
    0.65
    Activations Density 0.002%

    No Known Activations