© 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. 10263
    Prev
    Next
    INDEX
    Explanations

    poetry, poetic, poet

    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
     boyunca
    2.83
    bore
    2.72
    paused
    2.69
     percorso
    2.59
     piecewise
    2.50
    sheet
    2.49
    ところで
    2.49
    葚
    2.43
    sia
    2.42
     بقول
    2.41
    POSITIVE LOGITS
     dobu
    3.42
    መሳሳይ
    2.98
    entially
    2.95
    こと
    2.82
    тпу
    2.78
    centaje
    2.71
    atoes
    2.70
    राणिक
    2.68
    ্ড
    2.67
    assium
    2.66
    Activations Density 0.117%

    No Known Activations