© 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. 10161
    Prev
    Next
    INDEX
    Explanations

    policy numbers, development, enforcement

    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
    تری
    3.21
    strain
    2.92
     ofstream
    2.90
    mul
    2.74
    ्हे
    2.74
    anın
    2.73
    mkdir
    2.71
    ๐
    2.70
    nen
    2.67
    ===========
    2.66
    POSITIVE LOGITS
     odnosno
    3.01
     raison
    2.97
     udal
    2.95
    𝐢
    2.91
    𝐞
    2.89
    holders
    2.83
    она
    2.78
    ofinstagram
    2.73
     gravi
    2.60
    ła
    2.59
    Activations Density 0.014%

    No Known Activations