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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-262K
    4. 6889
    Prev
    Next
    INDEX
    Explanations

    production Line conditions

    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
     electors
    1.17
     Wrath
    1.05
     pedidos
    1.05
     curfew
    1.04
    LT
    1.04
    </iframe>
    1.04
     quotidien
    1.04
     smother
    1.03
     गुणवत्ता
    1.03
    ϫ
    1.01
    POSITIVE LOGITS
     fame
    1.26
     أنّ
    1.23
    a
    1.16
     أنه
    1.09
    quy
    1.08
    筒
    1.06
     сила
    1.06
    ণীর
    1.04
     îi
    1.04
    một
    1.04
    Activations Density 0.000%

    No Known Activations