© 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. 136797
    Prev
    Next
    INDEX
    Explanations

    dynamic route parameters

    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
     Disponible
    0.46
     온
    0.45
    VIDENCE
    0.44
     betracht
    0.43
     밤
    0.42
     was
    0.41
     следует
    0.41
     обратить
    0.41
     ഉണ്ട്
    0.40
     composure
    0.40
    POSITIVE LOGITS
    পদে
    0.44
    TRA
    0.42
    creens
    0.42
     pTM
    0.42
    |
    0.42
     नींबू
    0.41
    ي
    0.41
     pico
    0.41
     नम्बर
    0.41
     kindle
    0.41
    Activations Density 0.017%

    No Known Activations