© 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. 3610
    Prev
    Next
    INDEX
    Explanations

    library usage

    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
    CTION
    1.70
    이기
    1.63
    し
    1.58
    מי
    1.57
    мум
    1.53
     Somos
    1.53
    ﻢ
    1.48
     项目
    1.48
    ની
    1.45
     ato
    1.43
    POSITIVE LOGITS
    oflavin
    1.84
    ס
    1.62
    ina
    1.55
    きます
    1.48
    rary
    1.46
    les
    1.45
    던
    1.45
     festgestellt
    1.45
    res
    1.44
    onuclease
    1.44
    Activations Density 0.101%

    No Known Activations