© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 226360
    Prev
    Next
    INDEX
    Explanations

    based initiatives

    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
    ewood
    0.50
     \
    0.47
    AMS
    0.46
     ت
    0.46
    }\
    0.46
    YB
    0.46
    address
    0.45
     博文
    0.45
    \
    0.45
    apped
    0.45
    POSITIVE LOGITS
     १९
    0.51
    Ҷ
    0.50
    ోతి
    0.50
    Khi
    0.49
     आहे
    0.48
     преступ
    0.48
    withId
    0.48
     нерав
    0.47
     sacer
    0.46
     १२
    0.46
    Activations Density 0.000%

    No Known Activations