© 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. 111522
    Prev
    Next
    INDEX
    Explanations

    comments regarding

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

    Baywatch, Hawaii, Vadodara, your

    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
    Id
    0.57
     -
    0.53
    at
    0.49
     pound
    0.49
    Word
    0.48
    0.48
     Word
    0.48
     وعلى
    0.45
     disciplinary
    0.45
     I
    0.45
    POSITIVE LOGITS
     sentimento
    0.56
     உறுப்பின
    0.54
     âmbito
    0.54
    avond
    0.53
     ಸಂತ
    0.51
     alegria
    0.51
     aimé
    0.51
    愺
    0.51
    蓥
    0.51
     kaldığımız
    0.50
    Activations Density 0.000%

    No Known Activations