© 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-262K
    7. 26279
    Prev
    Next
    INDEX
    Explanations

    comfortable sharing information

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    唖
    0.44
    碑
    0.39
    ے۔
    0.37
     ਵਿਚ
    0.37
     চো
    0.37
     பண்ண
    0.36
     Fleurit
    0.35
    >);
    0.35
    惡
    0.35
    訓
    0.35
    POSITIVE LOGITS
     disclosure
    1.96
     disclosing
    1.94
     disclose
    1.93
     discloses
    1.82
     revealing
    1.80
     divulge
    1.80
     reveal
    1.77
     divul
    1.76
     disclosures
    1.75
     disclosed
    1.72
    Activations Density 0.021%

    No Known Activations