© 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. 120574
    Prev
    Next
    INDEX
    Explanations

    legal and technical terms

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

    navigating protection spiritual attached leaf

    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
    y
    0.48
    o
    0.44
    পূর্বে
    0.43
    デフォルト
    0.42
     fatigue
    0.42
     Bax
    0.42
     aggrieved
    0.42
     economics
    0.42
     impairments
    0.42
    james
    0.42
    POSITIVE LOGITS
     Prompt
    0.53
    Prompt
    0.50
    藿
    0.48
    ाइन
    0.45
    培训
    0.44
     अपहरण
    0.44
    绯
    0.44
    辫
    0.44
    ğı
    0.43
     tiket
    0.43
    Activations Density 0.000%

    No Known Activations