© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 100487
    Prev
    Next
    INDEX
    Explanations

    body sculpting, best place, you want

    np_acts-logits-general · gemini-2.5-flash-lite

    legal, medical, judgments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     යුතු
    0.48
    朹
    0.48
    '`--
    0.48
    ?>"
    0.47
    ovaniyu
    0.46
     estadounid
    0.45
    కునే
    0.44
     ರೂ
    0.44
    やや
    0.44
    apaccay
    0.44
    POSITIVE LOGITS
    ؤال
    0.55
    ц
    0.51
    бі
    0.50
     judgmental
    0.50
    鸨
    0.49
    ни
    0.48
    ին
    0.48
     belief
    0.47
    ージャー
    0.47
    ція
    0.46
    Activations Density 0.000%

    No Known Activations