© 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-262K
    7. 7232
    Prev
    Next
    INDEX
    Explanations

    in, with, within

    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
    0
    0.67
     want
    0.57
    bs
    0.54
    I
    0.54
     ơi
    0.50
     voulez
    0.50
    ug
    0.50
    gh
    0.49
     conceive
    0.49
    Q
    0.47
    POSITIVE LOGITS
     Chinatown
    0.63
     Halloween
    0.57
     lingerie
    0.57
     Silverstone
    0.57
    једина
    0.56
     Premiere
    0.56
     România
    0.56
    órias
    0.56
    孖
    0.55
     weekend
    0.55
    Activations Density 0.000%

    No Known Activations