© 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. 132276
    Prev
    Next
    INDEX
    Explanations

    published, working, stars, reliable

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

    exploits and objectifies

    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
    系統
    0.57
    intégration
    0.49
    socks
    0.48
    羥
    0.47
    élo
    0.46
    peanut
    0.45
    antal
    0.44
     referido
    0.43
    鎳
    0.43
    銨
    0.43
    POSITIVE LOGITS
     ceased
    0.44
     हाइट
    0.41
     коне
    0.40
     ற
    0.40
    Cao
    0.40
    Smaller
    0.40
     unser
    0.39
     hart
    0.38
     acabou
    0.38
    Def
    0.38
    Activations Density 0.000%

    No Known Activations