© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 115980
    Prev
    Next
    INDEX
    Explanations

    formal closing phrases

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

    closing remarks

    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
    Not in Any Lists

    No Comments

    Negative Logits
    كلمنا
    0.43
     هن
    0.40
    ेटा
    0.40
    霉
    0.38
    胗
    0.37
     მო
    0.37
     फै
    0.37
     പ്രതി
    0.37
    фото
    0.36
     니
    0.36
    POSITIVE LOGITS
     Sincerely
    0.58
     Regards
    0.48
    posed
    0.47
    Regards
    0.47
    ident
    0.46
    Sincerely
    0.46
    cing
    0.46
     climbs
    0.46
    assing
    0.45
     Dated
    0.45
    Activations Density 0.021%

    No Known Activations