© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 47668
    Prev
    Next
    INDEX
    Explanations

    stating intentions or facts upfront

    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_40_width_65k_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
    ل
    0.49
    م
    0.48
     hammering
    0.45
     لحظ
    0.45
    א
    0.44
     المؤ
    0.43
     bouts
    0.43
    螫
    0.42
    点头
    0.42
    い
    0.41
    POSITIVE LOGITS
     Preferences
    0.46
     Policies
    0.45
     অপে
    0.44
    歉
    0.44
     intentions
    0.44
    POLICY
    0.44
    preferences
    0.43
     Expectations
    0.42
    enz
    0.42
     Policy
    0.41
    Activations Density 0.019%

    No Known Activations