© 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. 53640
    Prev
    Next
    INDEX
    Explanations

    kitchen items and clothing

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

    harmful potential consequences

    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
     یو
    0.51
     პირ
    0.49
     хоккей
    0.47
     arasındaki
    0.47
    सीसीआई
    0.46
    といえば
    0.46
     会
    0.46
    łka
    0.46
     перший
    0.45
     monopolist
    0.44
    POSITIVE LOGITS
     Familien
    0.57
     Temperaturen
    0.55
     Pozn
    0.51
     Leistungen
    0.50
     Vire
    0.50
     Patterns
    0.49
    點
    0.49
     Glowing
    0.48
     Kennt
    0.48
     Vim
    0.48
    Activations Density 0.000%

    No Known Activations