© 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. 27354
    Prev
    Next
    INDEX
    Explanations

    imperative that, with it, for every party

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

    descriptions or statements

    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
     schol
    0.42
    oun
    0.41
    구나
    0.41
    Gon
    0.40
     coursework
    0.40
    िल्ली
    0.39
    Codigo
    0.39
     -->
    0.38
    Students
    0.38
    ="#"
    0.37
    POSITIVE LOGITS
     eyeing
    0.49
    പ്പോഴും
    0.48
    男友
    0.46
    dari
    0.46
     збіль
    0.46
     sekarang
    0.45
    早已
    0.44
     broader
    0.44
    ার্জি
    0.44
     stej
    0.44
    Activations Density 0.000%

    No Known Activations