© 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. 9-GEMMASCOPE-2-RES-262K
    7. 8656
    Prev
    Next
    INDEX
    Explanations

    protocol

    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
    з
    4.26
    ین
    3.59
    ت
    3.56
    ा
    3.25
    জন
    3.11
    ン
    3.05
    cedented
    2.99
    تف
    2.97
    ように
    2.87
    োহণ
    2.86
    POSITIVE LOGITS
    ्य
    3.67
    م
    3.19
    $('#
    3.12
    ো
    3.06
    t
    3.00
    ηση
    2.98
    вання
    2.98
    𝗮
    2.94
    minded
    2.93
    Translatef
    2.90
    Activations Density 0.098%

    No Known Activations