© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 20673
    Prev
    Next
    INDEX
    Explanations

    warnings about cautions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    钢
    0.54
    ície
    0.52
    轨道
    0.51
     найкра
    0.51
    芘
    0.51
     кора
    0.50
     réelle
    0.50
     ενεργ
    0.50
     ули
    0.50
     працю
    0.49
    POSITIVE LOGITS
     regimens
    0.43
    Monday
    0.42
     legitim
    0.41
     detoxification
    0.41
    em
    0.39
     hiding
    0.39
     increase
    0.38
     alignment
    0.38
    Ο
    0.38
     scaling
    0.38
    Activations Density 0.001%

    No Known Activations