© 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. 17-GEMMASCOPE-2-RES-16K
    7. 13572
    Prev
    Next
    INDEX
    Explanations

    modified for purpose

    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_17_width_16k_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
     transversely
    0.79
    <unused572>
    0.74
     longitudinally
    0.67
     ulang
    0.63
     mao
    0.61
     interstitiis
    0.61
     oficialmente
    0.61
    ifizierung
    0.61
    dfunding
    0.60
    <unused2158>
    0.60
    POSITIVE LOGITS
    আমার
    0.68
    묻
    0.63
     આપણા
    0.63
     내가
    0.61
     redonde
    0.59
     আমি
    0.58
     schrift
    0.57
     okol
    0.57
     salinity
    0.56
     غير
    0.56
    Activations Density 0.049%

    No Known Activations