© 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. 180533
    Prev
    Next
    INDEX
    Explanations

    repeatedly whether, protect the, perennial insecurities

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

    circular dependencies or imports

    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
    詼
    0.60
    朋友們
    0.57
    ポルト
    0.50
    الية
    0.50
     ين
    0.49
    ريم
    0.48
    غيرة
    0.46
     يع
    0.46
     對
    0.46
     يعتبر
    0.46
    POSITIVE LOGITS
     MCU
    0.48
     McInt
    0.48
     Cortex
    0.48
     magnification
    0.46
     MgO
    0.46
     offensively
    0.45
     supplemental
    0.44
     penetrating
    0.44
     Rune
    0.44
     hashing
    0.44
    Activations Density 0.000%

    No Known Activations