© 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. 59835
    Prev
    Next
    INDEX
    Explanations

    to / or hair

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

    path/to/your or path\to\your

    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
     نہيں
    0.49
     Дж
    0.49
    дцать
    0.47
     እንኳ
    0.46
     យើង
    0.46
    ochlorite
    0.46
     №
    0.46
     شي
    0.45
    Raquete
    0.45
     mobilized
    0.45
    POSITIVE LOGITS
    手游
    0.48
    에서
    0.45
    角色
    0.43
    guas
    0.42
    """
    0.42
    🐙
    0.41
    গরে
    0.40
    游戏
    0.40
    oplayer
    0.40
    愺
    0.40
    Activations Density 0.000%

    No Known Activations