© 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. 9345
    Prev
    Next
    INDEX
    Explanations

    recognized by, direction

    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
    <0xF4>
    1.35
    عيب
    1.31
     اړه
    1.28
    cerr
    1.23
    conductivity
    1.23
    ipid
    1.22
    isierung
    1.21
    رمز
    1.19
    ك
    1.19
    Adi
    1.18
    POSITIVE LOGITS
     Ahí
    1.12
     ao
    1.12
     către
    1.07
    НУ
    1.03
     слова
    1.00
    ITIES
    1.00
     overwhelm
    1.00
    协商
    1.00
    省
    0.99
     près
    0.98
    Activations Density 0.000%

    No Known Activations