© 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. 9-GEMMASCOPE-2-RES-16K
    7. 1279
    Prev
    Next
    INDEX
    Explanations

    script, scripting, scripts

    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_9_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
    नियां
    2.99
     exclaimed
    2.89
    fangen
    2.85
    ように
    2.78
     sworn
    2.74
     conglomerate
    2.73
    م
    2.71
     Rename
    2.70
    Rename
    2.63
    Substituting
    2.62
    POSITIVE LOGITS
    માં
    2.97
    ০
    2.94
    ו
    2.85
    uoso
    2.82
    o
    2.81
    ه
    2.67
    at
    2.55
    े
    2.55
    ுள்ள
    2.54
    robust
    2.51
    Activations Density 0.319%

    No Known Activations