© 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. 12340
    Prev
    Next
    INDEX
    Explanations

    after a series

    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
    thinkable
    1.02
    :“
    0.83
    Waar
    0.82
    ємо
    0.82
    Creating
    0.81
     menciptakan
    0.79
     Horizons
    0.74
    Poi
    0.74
     tractable
    0.73
     objectivity
    0.73
    POSITIVE LOGITS
    仅
    0.81
     after
    0.78
     accidentally
    0.77
    额外
    0.76
     After
    0.75
     dodat
    0.75
     باوجود
    0.74
     wasn
    0.74
    僅
    0.73
     unsupported
    0.73
    Activations Density 0.263%

    No Known Activations