© 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. 18934
    Prev
    Next
    INDEX
    Explanations

    maintain cardiovascular health

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

    racial, snow, mother, research, jobs

    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
     SOLUTION
    0.47
     некоторых
    0.44
    ning
    0.44
     máxima
    0.43
     Shit
    0.43
     некоторы
    0.42
    zione
    0.42
     G
    0.41
     група
    0.41
    的一些
    0.41
    POSITIVE LOGITS
     sexuality
    0.53
     fascism
    0.53
     hoodies
    0.50
    ייס
    0.50
    oucault
    0.50
     gyne
    0.50
    ImgBoard
    0.49
     binoculars
    0.48
    𒊏
    0.47
     gafas
    0.47
    Activations Density 0.000%

    No Known Activations