© 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. 35762
    Prev
    Next
    INDEX
    Explanations

    mold, multicast, multimodal, names

    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
    urile
    1.61
    ва
    1.49
    ación
    1.49
    up
    1.48
    𝐭
    1.46
     компанией
    1.40
    zmdi
    1.39
     vuonna
    1.38
    യി
    1.38
     રિ
    1.35
    POSITIVE LOGITS
    ،
    2.27
    و
    1.85
    ፣
    1.80
    ，
    1.77
    en
    1.67
    ע
    1.64
    وية
    1.63
    ၊
    1.63
    。
    1.46
    done
    1.37
    Activations Density 0.001%

    No Known Activations