© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 19908
    Prev
    Next
    INDEX
    Explanations

    scales proportionally or logarithmically

    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_22_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
     ریکارڈ
    0.89
     взгля
    0.87
    銹
    0.86
    㻐
    0.84
    挸
    0.84
     marcó
    0.83
    ന്ഥ
    0.82
    寇
    0.81
     teenage
    0.81
    [multimodal]
    0.81
    POSITIVE LOGITS
    zinho
    0.80
     Tw
    0.79
    y
    0.76
     Twitch
    0.76
    ्यां
    0.72
    gras
    0.71
     Inc
    0.70
    கள்
    0.69
     Bear
    0.68
    फ
    0.68
    Activations Density 0.000%

    No Known Activations