Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 7737
    Prev
    Next
    INDEX
    Explanations

    conflicts and states

    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
    s
    1.82
    ات
    1.59
     Ums
    1.32
    اند
    1.27
    ের
    1.26
    sene
    1.24
     điển
    1.20
    ség
    1.15
    sellers
    1.11
    $\$
    1.11
    POSITIVE LOGITS
    ного
    1.62
    ка
    1.50
     percepción
    1.46
    ство
    1.43
    ikuti
    1.40
    el
    1.40
    ์
    1.38
    transfected
    1.38
    ное
    1.37
    spapers
    1.37
    Activations Density 0.000%

    No Known Activations