© 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. 240874
    Prev
    Next
    INDEX
    Explanations

    mulch, mouse deterrents, management beliefs

    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
    感
    0.53
    Temple
    0.48
     problème
    0.47
    ﻧ
    0.47
    ເຮັດ
    0.46
    重
    0.46
    ды
    0.45
    γραφ
    0.45
    大
    0.45
    ро
    0.45
    POSITIVE LOGITS
     Chief
    0.50
     Finance
    0.50
     æ
    0.49
     Characters
    0.48
     CFO
    0.47
     Rely
    0.47
     relying
    0.46
     industries
    0.44
     गढ़
    0.44
     उद्योगों
    0.44
    Activations Density 0.001%

    No Known Activations