© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 11328
    Prev
    Next
    INDEX
    Explanations

    formatting or structural elements

    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
    ς
    1.45
    cómo
    1.38
    то
    1.35
    Бі
    1.34
    przy
    1.29
     unsatisfactory
    1.27
    các
    1.26
    그러나
    1.23
    вы
    1.18
    ctrine
    1.16
    POSITIVE LOGITS
    ной
    1.49
    an
    1.42
    ი
    1.40
    ↵
    1.37
    ak
    1.33
    ين
    1.32
    ीन
    1.32
    ാ
    1.32
    </td>
    1.27
    ان
    1.23
    Activations Density 0.018%

    No Known Activations