© 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-262K
    7. 10949
    Prev
    Next
    INDEX
    Explanations

    findings, explanations, and context

    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_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
     personalizar
    0.81
    别人
    0.79
     அறிவியல்
    0.76
    ມັນ
    0.75
    Encryption
    0.75
    Elemental
    0.73
    Elastic
    0.72
    <unused1798>
    0.72
    Kalau
    0.72
    楊
    0.71
    POSITIVE LOGITS
    和社会
    0.82
     superimposed
    0.72
    ings
    0.69
     exemplified
    0.68
     underpinned
    0.66
     steeped
    0.65
    đena
    0.63
     अरुण
    0.62
    šće
    0.62
     rejecting
    0.61
    Activations Density 0.664%

    No Known Activations