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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 3904
    Prev
    Next
    INDEX
    Explanations

    arguably the

    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
    ب
    1.56
    r
    1.54
    مي
    1.49
    ли
    1.37
    ל
    1.36
    و
    1.35
    .!
    1.22
    .
    1.21
    ar
    1.17
    l
    1.17
    POSITIVE LOGITS
    得上
    1.45
    ━━
    1.38
     arguably
    1.30
    说
    1.30
    始终
    1.24
    ム
    1.24
    য়ের
    1.23
     besten
    1.23
    ≜
    1.22
    ющим
    1.21
    Activations Density 0.068%

    No Known Activations