© 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. 29249
    Prev
    Next
    INDEX
    Explanations

    based around

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

    arduino, PowerShell, lives, deaths

    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
    物
    0.48
    責
    0.43
    退
    0.42
    珍
    0.42
    かく
    0.42
    п
    0.42
    उँ
    0.42
    ափ
    0.41
     lifts
    0.41
    モノ
    0.40
    POSITIVE LOGITS
     الحالي
    0.54
    skih
    0.53
    Beim
    0.52
     Difer
    0.52
    inhos
    0.51
     עם
    0.51
    araham
    0.50
    şen
    0.50
    Memento
    0.50
     अराज
    0.50
    Activations Density 0.000%

    No Known Activations