© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 146994
    Prev
    Next
    INDEX
    Explanations

    required property

    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
    lines
    0.78
     kary
    0.73
    Gast
    0.72
     সার্জ
    0.71
    ₴
    0.71
    渦
    0.70
     запя
    0.70
    NSLog
    0.69
     Gast
    0.68
    <0x8C>
    0.67
    POSITIVE LOGITS
     believing
    0.76
     SIDE
    0.71
     believes
    0.70
     side
    0.70
     screwing
    0.69
    பெரும்
    0.69
     Derived
    0.68
     believe
    0.68
    ாரா
    0.68
     obstructed
    0.67
    Activations Density 0.001%

    No Known Activations