© 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. 4337
    Prev
    Next
    INDEX
    Explanations

    lists items or code snippets

    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
    ל
    1.84
    ل
    1.75
    িক
    1.74
    ไม่ใช่
    1.63
    ش
    1.63
    ق
    1.58
    шей
    1.47
    ৯
    1.47
    不由
    1.45
    ри
    1.42
    POSITIVE LOGITS
    féle
    1.64
     ventes
    1.59
     chimiques
    1.59
    Eksterne
    1.58
    ال
    1.54
    ja
    1.52
     siento
    1.52
     gotas
    1.52
     andare
    1.51
     iā
    1.50
    Activations Density 0.000%

    No Known Activations