© 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. 201378
    Prev
    Next
    INDEX
    Explanations

    Status, page, game

    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
    שת
    0.53
    zelfde
    0.52
    пів
    0.50
    扇
    0.47
    řed
    0.47
     വിദ്യാ
    0.47
    విద్య
    0.46
    řez
    0.45
    šten
    0.45
    зара
    0.45
    POSITIVE LOGITS
     I
    0.59
    I
    0.55
     to
    0.53
     walnuts
    0.46
     you
    0.46
     н
    0.46
     !
    0.45
     sweetheart
    0.45
     occasional
    0.44
    Baby
    0.44
    Activations Density 0.000%

    No Known Activations