© 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. 145966
    Prev
    Next
    INDEX
    Explanations

    Southern Poverty Law Center

    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
     Probate
    0.74
     Finest
    0.70
    চে
    0.69
    કમ
    0.67
    inei
    0.66
    inem
    0.66
    碧
    0.65
    irem
    0.65
     datang
    0.64
    𝙿
    0.64
    POSITIVE LOGITS
     ලබා
    0.77
     देव
    0.75
     baseUrl
    0.71
     لجنة
    0.70
    欹
    0.66
    ￱
    0.66
     convincingly
    0.66
     weight
    0.66
     gable
    0.65
     accordingly
    0.65
    Activations Density 0.002%

    No Known Activations