© 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. 22-GEMMASCOPE-2-RES-65K
    7. 8533
    Prev
    Next
    INDEX
    Explanations

    Okay, let's breakdown

    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_22_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
     foll
    0.74
     ન
    0.67
     killed
    0.67
    إ
    0.66
     f
    0.63
     Dec
    0.62
     સ
    0.61
     *
    0.61
     மூ
    0.61
     ah
    0.60
    POSITIVE LOGITS
    ropathy
    1.06
    isserie
    1.04
    istas
    1.03
    ยนตร์
    1.03
    endants
    1.00
    ives
    1.00
    ivism
    0.99
    ensible
    0.99
    ifers
    0.96
    opia
    0.96
    Activations Density 0.139%

    No Known Activations