© 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. 205121
    Prev
    Next
    INDEX
    Explanations

    steps for tasks

    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
     mảnh
    0.49
     dhatu
    0.44
     connaître
    0.43
    ２
    0.43
     dbcontext
    0.42
     hefyd
    0.42
    YW
    0.41
    кування
    0.41
     apparaître
    0.41
     pradesh
    0.41
    POSITIVE LOGITS
    a
    0.49
    idon
    0.48
    aid
    0.47
    sic
    0.47
    approche
    0.47
    save
    0.46
    everyone
    0.46
    child
    0.46
    songs
    0.46
    aver
    0.46
    Activations Density 0.003%

    No Known Activations