© 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. 225073
    Prev
    Next
    INDEX
    Explanations

    delivery or IRS actions

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

    agree, disagree, affect, remove

    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
     Antonio
    0.49
    Techn
    0.48
     Corps
    0.43
     Núñez
    0.43
     촉
    0.43
    πος
    0.42
     Nanjing
    0.42
    Antonio
    0.42
     Easier
    0.42
    ುತ್ತವೆ
    0.42
    POSITIVE LOGITS
    е
    0.57
     производителя
    0.51
    а
    0.49
     effectuer
    0.49
    го
    0.46
    ெ
    0.46
     इसको
    0.46
     ስለዚህ
    0.46
    ק
    0.46
     placed
    0.45
    Activations Density 0.001%

    No Known Activations