© 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. 219962
    Prev
    Next
    INDEX
    Explanations

    range of, your individual

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

    ****: key changes and why

    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
    렸
    0.54
     новом
    0.50
     thóc
    0.50
    راہیم
    0.49
    жном
    0.48
    нном
    0.47
     いっ
    0.47
     focussed
    0.47
    人士
    0.46
    の変化
    0.45
    POSITIVE LOGITS
     Kru
    0.47
    formas
    0.46
     Esso
    0.45
     semelhantes
    0.45
     breakfasts
    0.43
    g
    0.43
    躁
    0.42
     Tutt
    0.42
    EUI
    0.42
    ELI
    0.42
    Activations Density 0.000%

    No Known Activations