© 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. 203970
    Prev
    Next
    INDEX
    Explanations

    foreign language content

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

    strategy and roadmap aligned

    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
    тта
    0.48
    끙
    0.46
    ﻚ
    0.44
    埬
    0.44
    LOCATION
    0.44
    вається
    0.43
    휙
    0.43
    вом
    0.43
     огром
    0.43
    ровки
    0.43
    POSITIVE LOGITS
    alos
    0.47
     விடு
    0.47
    edel
    0.46
    </b>
    0.46
     نخ
    0.46
     سائ
    0.45
    lees
    0.45
    fut
    0.45
     ለአ
    0.44
     Tiro
    0.43
    Activations Density 0.000%

    No Known Activations