© 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. 64815
    Prev
    Next
    INDEX
    Explanations

    your next

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

    questioning stereotypes or assumptions

    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
     прош
    0.50
    を獲得
    0.48
     organis
    0.46
    ’-
    0.45
     supergiants
    0.45
     saad
    0.45
    CEEDINGS
    0.44
     Mereka
    0.44
    で開催
    0.44
     inkluder
    0.44
    POSITIVE LOGITS
    Cut
    0.53
     a
    0.52
    A
    0.48
    Parsed
    0.48
    States
    0.48
    Converted
    0.46
    дом
    0.46
     an
    0.45
    ู่
    0.45
    Shr
    0.45
    Activations Density 0.000%

    No Known Activations