© 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. 96706
    Prev
    Next
    INDEX
    Explanations

    control your actions

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

    knowledge and mindset

    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
     accrue
    0.48
    ت
    0.47
    };
    0.47
    ил
    0.46
    デス
    0.46
    個人
    0.46
    اا
    0.45
    ﻧ
    0.45
    人間
    0.44
    可能
    0.44
    POSITIVE LOGITS
     Arithmetic
    0.59
    itia
    0.49
     Heiz
    0.49
     Piazza
    0.49
    vious
    0.48
    ंबा
    0.47
     Patti
    0.46
    perature
    0.46
     Hua
    0.46
     अभिभाव
    0.46
    Activations Density 0.000%

    No Known Activations