© 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. 127313
    Prev
    Next
    INDEX
    Explanations

    Names, individuals, and things

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

    when you

    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
    ョン
    0.48
     emphasises
    0.47
     వచ్చిన
    0.47
    Callories
    0.46
    식회사
    0.46
     aspectRatio
    0.46
     Kxh
    0.46
    엷
    0.46
     వెళ్లి
    0.45
     낮은
    0.45
    POSITIVE LOGITS
    u
    0.46
    0.44
     Boston
    0.43
    BRE
    0.43
     Casper
    0.43
     Bulldog
    0.42
     Strat
    0.42
     B
    0.42
     Biomedical
    0.42
     Beagle
    0.42
    Activations Density 0.000%

    No Known Activations