© 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. 24-GEMMASCOPE-2-RES-262K
    7. 17137
    Prev
    Next
    INDEX
    Explanations

    finding values or versions

    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_24_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
    ﻥ
    1.78
    นะคะ
    1.75
    を入力
    1.73
    لم
    1.70
    を表示
    1.69
    ыр
    1.67
    ын
    1.64
     Preise
    1.63
    ى
    1.58
     фонбет
    1.52
    POSITIVE LOGITS
     Vict
    1.70
     Ambul
    1.63
    coelastic
    1.61
    acious
    1.58
     entraî
    1.48
    átiles
    1.48
     Enh
    1.46
     succumb
    1.45
    रासत
    1.45
     accom
    1.42
    Activations Density 0.000%

    No Known Activations