© 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. 146055
    Prev
    Next
    INDEX
    Explanations

    right or south end

    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
     peasantry
    0.67
    >^
    0.67
     .^{
    0.67
     mortality
    0.64
     Mortality
    0.64
    AndroidJUnit
    0.64
    ​​​​
    0.64
     calmness
    0.63
    }~\
    0.63
     casualties
    0.63
    POSITIVE LOGITS
    .$
    0.78
    ुक
    0.76
    வக
    0.74
    ركه
    0.70
     прось
    0.70
    父親
    0.69
    欄
    0.68
    硫酸
    0.68
     fått
    0.68
    擾
    0.67
    Activations Density 0.001%

    No Known Activations