© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 11425
    Prev
    Next
    INDEX
    Explanations

    with other or sometimes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    டுகள்
    0.46
    ళ్ళు
    0.42
    <0xBC>
    0.42
    ён
    0.41
    ্টেন
    0.41
     gasolina
    0.41
    ༣
    0.40
     الاي
    0.39
    变量
    0.39
    ωση
    0.38
    POSITIVE LOGITS
    âtel
    0.54
     Angola
    0.53
    に関する
    0.50
    qualiter
    0.50
     Áng
    0.50
    及び
    0.49
     entrop
    0.47
    asitriangular
    0.47
    langan
    0.47
     व
    0.46
    Activations Density 0.001%

    No Known Activations