© 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. 39170
    Prev
    Next
    INDEX
    Explanations

    Yen film

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

    within, used, from, generate

    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
    內容
    0.59
    内容
    0.52
    塢
    0.51
    容
    0.48
    م
    0.46
    蹌
    0.45
    发布
    0.45
    在這個
    0.45
     buffs
    0.45
    坞
    0.45
    POSITIVE LOGITS
     માન
    0.48
     বোল
    0.48
    alic
    0.46
    preferably
    0.46
     خواهد
    0.46
    CurrentImageData
    0.45
     disebabkan
    0.44
    isDisabled
    0.43
     દર્
    0.43
     Boliv
    0.43
    Activations Density 0.001%

    No Known Activations