© 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. 63259
    Prev
    Next
    INDEX
    Explanations

    information, action, policy

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

    financial risk or assistance

    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
    🖉
    0.61
     Änderungen
    0.52
    ിയ്
    0.51
     değişiklik
    0.50
     rewriting
    0.49
    ForSettings
    0.49
    nA
    0.49
    .(\
    0.48
     অনুরোধ
    0.47
    ক্ষেত্র
    0.47
    POSITIVE LOGITS
    人士
    0.48
     the
    0.46
     zenith
    0.44
    住
    0.44
     peoples
    0.42
    idar
    0.42
    ول
    0.41
    ↵↵
    0.40
    ウ
    0.40
     Islam
    0.39
    Activations Density 0.002%

    No Known Activations