© 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. 200551
    Prev
    Next
    INDEX
    Explanations

    legal and financial contexts

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

    song lyrics and lists

    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
    ວ
    0.50
    енча
    0.46
    ニメ
    0.45
    čila
    0.45
    메이션
    0.45
    ﻓ
    0.44
    asem
    0.44
    ﻫ
    0.44
     Người
    0.43
    創意
    0.43
    POSITIVE LOGITS
     §
    0.50
     acquies
    0.49
     Squadron
    0.48
     グレー
    0.48
     Pythagorean
    0.45
     dominions
    0.45
     Hemat
    0.45
    ota
    0.45
    akukan
    0.44
     Mathematical
    0.44
    Activations Density 0.000%

    No Known Activations