© 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. 246993
    Prev
    Next
    INDEX
    Explanations

    actions to do

    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
    Negative Logits
    are
    0.49
    od
    0.49
     seu
    0.49
     /
    0.46
     Foods
    0.45
    NA
    0.44
     page
    0.44
     หลัก
    0.44
     trink
    0.44
    ixes
    0.44
    POSITIVE LOGITS
    ப்புகளில்
    0.47
    改善
    0.46
    音
    0.46
    乘
    0.44
    URNIZOR
    0.44
    豚
    0.44
    琶
    0.44
    พย์
    0.44
    DebugType
    0.43
    вто
    0.43
    Activations Density 0.000%

    No Known Activations