© 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. 26996
    Prev
    Next
    INDEX
    Explanations

    legacy and deeds

    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
    分离
    0.46
    稳
    0.46
    ódromo
    0.45
    一个小
    0.44
     καν
    0.43
    镇
    0.43
    区域
    0.42
     அ
    0.42
    澄
    0.42
     구성
    0.41
    POSITIVE LOGITS
     pensions
    0.54
     investir
    0.53
     mortgages
    0.52
     invest
    0.50
     BOOKS
    0.48
     cancers
    0.47
     anual
    0.46
     tuvieron
    0.46
     books
    0.46
     retirees
    0.46
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.