© 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. 11603
    Prev
    Next
    INDEX
    Explanations

    book resource

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

    programming code

    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
     einzelnen
    0.31
    قر
    0.31
    এইচ
    0.31
     Brigham
    0.29
     antimony
    0.29
    Φ
    0.29
     Archibald
    0.28
     Botanic
    0.28
     Bryn
    0.28
     Cardiol
    0.28
    POSITIVE LOGITS
    에
    0.35
     Sudah
    0.34
     나가
    0.34
    에서
    0.34
     단
    0.33
     싫
    0.32
     큰
    0.31
     わ
    0.31
    విత
    0.31
     요즘
    0.31
    Activations Density 0.005%

    No Known Activations