© 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-16K
    7. 1117
    Prev
    Next
    INDEX
    Explanations

    various scripts, numbers

    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_16k_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
    1.45
    ك
    1.16
    Type
    1.05
    𝘀
    1.05
     begg
    1.03
    ს
    1.02
    ের
    1.01
    ς
    1.01
    пол
    1.00
    sans
    0.98
    POSITIVE LOGITS
    र
    1.29
    ার
    1.23
    าร
    1.19
    ל
    1.19
    이트
    1.16
    ísticas
    1.14
    ている
    1.13
    ১৪
    1.11
    ての
    1.11
    ル
    1.10
    Activations Density 0.105%

    No Known Activations