© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 10417
    Prev
    Next
    INDEX
    Explanations

    lists explanations

    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_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
    ्स
    1.14
    ean
    0.84
    rict
    0.79
    zelfde
    0.79
    aments
    0.79
    ရား
    0.77
    应该
    0.76
    ই
    0.75
    ição
    0.75
    ியுள்ளது
    0.74
    POSITIVE LOGITS
     meteen
    0.86
     unwittingly
    0.81
    氯
    0.80
    ø
    0.76
    ös
    0.73
     gesagt
    0.72
     lunch
    0.72
     Monaco
    0.72
     momenta
    0.71
     Jugend
    0.71
    Activations Density 0.166%

    No Known Activations