© 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. 37021
    Prev
    Next
    INDEX
    Explanations

    act of praising

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

    admiration and praise

    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
    s
    0.68
    ---------------
    0.64
    lll
    0.63
    ll
    0.61
     nightmares
    0.61
    ----------------
    0.60
    -----------
    0.58
     क्षार
    0.57
     питання
    0.56
     Liabilities
    0.56
    POSITIVE LOGITS
     praising
    0.94
     praise
    0.91
     praised
    0.91
     admire
    0.90
     lauded
    0.80
     admired
    0.79
     commend
    0.77
     প্রশংসা
    0.77
     commended
    0.75
    讚
    0.75
    Activations Density 0.054%

    No Known Activations