© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 9606
    Prev
    Next
    INDEX
    Explanations

    Spanish words and Quebec

    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_65k_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
    uhe
    0.55
    ib
    0.47
    atement
    0.44
     Reed
    0.43
     informée
    0.43
    uš
    0.43
    u
    0.43
    cheduling
    0.42
    im
    0.42
    ley
    0.42
    POSITIVE LOGITS
    使其
    0.69
     into
    0.62
     extensively
    0.50
    into
    0.49
     इनटू
    0.47
     Into
    0.47
     INTO
    0.46
    Into
    0.46
     onto
    0.44
    Ꮯ
    0.41
    Activations Density 0.272%

    No Known Activations