© 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. 109957
    Prev
    Next
    INDEX
    Explanations

    conditions for use

    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
    6
    0.47
     waffles
    0.47
    0.46
     Moisture
    0.46
     SHOW
    0.45
     precip
    0.44
     Dispute
    0.44
    习
    0.44
    ricing
    0.43
     GO
    0.43
    POSITIVE LOGITS
    fläche
    0.54
    qualität
    0.47
     المقدس
    0.46
    entwicklung
    0.45
    ើត
    0.45
     verlassen
    0.45
     ||=
    0.44
    llä
    0.44
    flächen
    0.44
    emene
    0.44
    Activations Density 0.000%

    No Known Activations