© 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. 27872
    Prev
    Next
    INDEX
    Explanations

    olive oil, BYOB, citations

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

    initial rollout, resistances, cut, video platform, rectangle

    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
    лан
    0.45
    궬
    0.45
    ጼ
    0.45
    گنڈ
    0.45
    篭
    0.45
    マン
    0.45
    Ꮬ
    0.45
    イト
    0.44
     frauds
    0.44
    ین
    0.44
    POSITIVE LOGITS
     CA
    0.53
     Business
    0.52
     PPP
    0.51
     WHO
    0.50
     DRA
    0.49
     पी
    0.49
     Venture
    0.49
    )
    0.49
     PA
    0.48
     CTA
    0.48
    Activations Density 0.001%

    No Known Activations