© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 2547
    Prev
    Next
    INDEX
    Explanations

    New <something>

    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
    样的
    2.28
    та
    2.23
    投资基金
    2.11
     arbeitet
    2.11
    戙
    2.08
    )。
    1.98
    },$
    1.94
    nance
    1.93
    学家
    1.92
     pertenc
    1.92
    POSITIVE LOGITS
    ו
    2.27
    fang
    2.17
    ing
    1.96
    ো
    1.95
    york
    1.73
    ened
    1.70
    spapers
    1.66
     fig
    1.63
    ar
    1.63
    og
    1.63
    Activations Density 0.159%

    No Known Activations