© 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-262K
    7. 5560
    Prev
    Next
    INDEX
    Explanations

    joint + collaboration modifiers

    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
    忑
    1.63
     mankind
    1.58
    ('-',
    1.53
    লাষ
    1.52
    ্দ
    1.48
    !=
    1.48
     곧
    1.48
    ený
    1.47
     Matters
    1.45
    isn
    1.44
    POSITIVE LOGITS
    ت
    2.78
    ن
    2.48
    ことで
    2.44
    و
    2.36
    elijke
    2.14
    от
    2.13
    ك
    2.08
    ent
    2.03
    s
    1.98
    ל
    1.96
    Activations Density 0.003%

    No Known Activations