© 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. 248243
    Prev
    Next
    INDEX
    Explanations

    especially use beef cool example withheld interior

    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
     marvell
    0.51
    сі
    0.49
    론
    0.49
     сім
    0.47
    땅
    0.46
    했고
    0.45
     Cynthia
    0.45
    ിച്ചി
    0.45
    ก
    0.45
    Ꮕ
    0.45
    POSITIVE LOGITS
    adores
    0.49
    em
    0.48
    ighet
    0.46
     χωρίς
    0.46
     (\%)
    0.45
     odl
    0.44
     ideales
    0.44
     নুর
    0.44
    ποιη
    0.44
     গঠন
    0.43
    Activations Density 0.001%

    No Known Activations