© 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-262K
    7. 145646
    Prev
    Next
    INDEX
    Explanations

    Completed or completeness

    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
     infallible
    0.87
     sharper
    0.81
     anguish
    0.78
    ἄ
    0.77
    forecast
    0.76
     xyz
    0.76
    ﭜ
    0.75
    eid
    0.75
    zechoslovak
    0.74
    等等
    0.74
    POSITIVE LOGITS
     powsta
    0.87
     Completed
    0.84
     completed
    0.83
    Completed
    0.81
     accompanies
    0.79
     completing
    0.79
     –
    0.75
     সম্প
    0.75
     completes
    0.75
     entste
    0.75
    Activations Density 0.002%

    No Known Activations