© 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. 209442
    Prev
    Next
    INDEX
    Explanations

    professional photographers

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

    breakdowns and explanations

    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
    -
    0.50
    ﻟ
    0.46
    Held
    0.46
    ズ
    0.46
    র্
    0.45
     held
    0.45
    備
    0.43
    ୋ
    0.43
    楽
    0.43
     reassuring
    0.42
    POSITIVE LOGITS
     অস্থির
    0.55
     настройки
    0.52
    ataya
    0.52
    !".
    0.51
     조건을
    0.50
     đức
    0.48
     dhinak
    0.48
     دنی
    0.47
     இள
    0.47
    !";
    0.47
    Activations Density 0.001%

    No Known Activations