© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 16213
    Prev
    Next
    INDEX
    Explanations

    URLs containing .org/ or .com/

    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
    ud
    0.44
    yan
    0.42
    ash
    0.42
    л
    0.41
    en
    0.40
    ba
    0.40
    ite
    0.40
    ed
    0.39
     highlighted
    0.39
    ન
    0.39
    POSITIVE LOGITS
     parable
    0.43
    好み
    0.41
    テナンス
    0.41
     psychos
    0.40
     ಆನಿ
    0.40
     tumors
    0.40
     arousal
    0.40
     Obstet
    0.39
     predators
    0.38
     constriction
    0.38
    Activations Density 0.009%

    No Known Activations