© 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. 109786
    Prev
    Next
    INDEX
    Explanations

    directions and instructions

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

    married, tire, neutral, authority

    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
     مكون
    0.52
     variedade
    0.48
     sensibilidad
    0.47
     એ
    0.46
    ynucle
    0.46
     decomposed
    0.45
     compuesta
    0.44
     enfermed
    0.44
     ຫຼື
    0.43
     composta
    0.43
    POSITIVE LOGITS
    kk
    0.52
    s
    0.50
     når
    0.49
    kor
    0.49
    shoes
    0.48
    ør
    0.47
    เมื่อ
    0.47
     laget
    0.46
    喵
    0.46
    Hvis
    0.46
    Activations Density 0.000%

    No Known Activations