© 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. 31-GEMMASCOPE-2-RES-65K
    7. 36058
    Prev
    Next
    INDEX
    Explanations

    conditions and their effects

    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_31_width_65k_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
    ט
    0.57
     Abschnitt
    0.53
    בר
    0.52
    مل
    0.50
    ותר
    0.49
    כר
    0.48
    جز
    0.48
    זרה
    0.47
    ב
    0.46
     Monate
    0.46
    POSITIVE LOGITS
    '
    0.47
    have
    0.46
    keep
    0.46
     пат
    0.45
     сове
    0.43
    full
    0.43
    listen
    0.43
    had
    0.43
    must
    0.42
     κι
    0.42
    Activations Density 0.003%

    No Known Activations