© 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. 20812
    Prev
    Next
    INDEX
    Explanations

    accelerating massive objects and computational models

    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
     presentar
    0.44
    antenna
    0.43
    .
    0.41
    :
    0.41
    ri
    0.41
    ington
    0.40
    enden
    0.40
    t
    0.40
     component
    0.40
    editable
    0.39
    POSITIVE LOGITS
    চারে
    0.45
    膂
    0.44
    ौन
    0.43
    𐰀
    0.43
     כול
    0.42
     wijze
    0.42
    朲
    0.42
    ęk
    0.42
     théor
    0.42
     საქ
    0.42
    Activations Density 0.000%

    No Known Activations