© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 2192
    Prev
    Next
    INDEX
    Explanations

    866-488-7386

    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
    zio
    0.77
    redient
    0.75
    ச்சூழ
    0.73
    dominant
    0.73
    ச்
    0.72
     इसको
    0.71
     zako
    0.69
    謗
    0.69
     EBIT
    0.69
    worm
    0.69
    POSITIVE LOGITS
     Trouver
    0.64
    अप्र
    0.63
     Pure
    0.62
    Hear
    0.61
    irii
    0.60
    voj
    0.60
    VC
    0.60
     דו
    0.59
     Rxg
    0.59
    াল
    0.59
    Activations Density 0.006%

    No Known Activations