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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 44214
    Prev
    Next
    INDEX
    Explanations

    examples, options, or listings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    お
    1.36
    Commande
    1.34
    س
    1.34
    Bs
    1.32
    ل
    1.32
    Started
    1.30
    that
    1.29
    Going
    1.28
    Carta
    1.27
    ার্চ
    1.27
    POSITIVE LOGITS
    يه
    1.10
    氯
    1.05
    牘
    1.03
     U
    1.02
    ை
    1.02
     thermoplastic
    0.98
    леду
    0.96
     Pops
    0.95
    ﺇ
    0.95
    тора
    0.95
    Activations Density 0.000%

    No Known Activations