© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 40485
    Prev
    Next
    INDEX
    Explanations

    leaving places / privacy / anywhere

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ד
    0.56
    դ
    0.55
     improper
    0.55
     uj
    0.55
     infection
    0.54
     arty
    0.54
    It
    0.54
     afbeelding
    0.54
     maestros
    0.52
    鿉
    0.52
    POSITIVE LOGITS
    компа
    0.60
    🏠
    0.57
     Turtles
    0.57
    SMS
    0.56
     thoải
    0.55
     Viitattu
    0.55
     በፍ
    0.54
    gown
    0.54
     спокойно
    0.53
     comfortably
    0.52
    Activations Density 0.021%

    No Known Activations