© 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. 51941
    Prev
    Next
    INDEX
    Explanations

    arrows and, taking place, tarde, 2, glycerin saddle, along with, online course

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

    security vulnerabilities and technical implementation

    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
     înainte
    0.46
    ificado
    0.46
     if
    0.43
     când
    0.41
    ifed
    0.41
     Asw
    0.41
    olol
    0.41
    谠
    0.41
    公正
    0.40
    leşik
    0.40
    POSITIVE LOGITS
     dones
    0.52
     Bewertungen
    0.49
    Ч
    0.49
    Rash
    0.46
    спорт
    0.46
    UB
    0.46
    पाठी
    0.46
     Спорт
    0.45
     باتیں
    0.45
    -
    0.44
    Activations Density 0.000%

    No Known Activations