© 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. 327
    Prev
    Next
    INDEX
    Explanations

    code/programmatic terms

    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
    s
    1.41
     ו
    1.34
    У
    1.30
    по
    1.30
    פ
    1.27
    𝐔
    1.27
    cellaneous
    1.24
    二氧化
    1.24
    ﻩ
    1.24
    ců
    1.22
    POSITIVE LOGITS
     inizia
    1.41
    ри
    1.39
    이면
    1.38
    ки
    1.37
    Didn
    1.37
    Prés
    1.32
    Aside
    1.31
    Alright
    1.30
     murs
    1.30
    Doesn
    1.29
    Activations Density 0.445%

    No Known Activations