© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 142959
    Prev
    Next
    INDEX
    Explanations

    descriptions starting with common verbs

    np_acts-logits-general · gemini-2.5-flash-lite

    breakdowns and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    джи
    0.44
     Ny
    0.42
    ytale
    0.42
    ख़
    0.42
    債
    0.41
    きた
    0.41
    ято
    0.41
    امن
    0.41
    див
    0.40
    ऑ
    0.40
    POSITIVE LOGITS
    Meter
    0.52
    মিটার
    0.50
    durationType
    0.49
    lastCursor
    0.47
     வைத்து
    0.47
    Course
    0.46
     ای
    0.45
    FolderName
    0.45
     dishes
    0.45
     রাখার
    0.44
    Activations Density 0.001%

    No Known Activations