© 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. 17976
    Prev
    Next
    INDEX
    Explanations

    good followed by common positive phrases

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

    good practice, morning, luck

    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
    1.01
    s
    0.92
    ের
    0.82
    കോ
    0.71
    ’;
    0.71
     mainu
    0.70
    Ớ
    0.68
     apne
    0.68
    ’
    0.68
     argparse
    0.66
    POSITIVE LOGITS
     good
    0.93
     खासा
    0.91
    ى
    0.91
     and
    0.89
    good
    0.89
    ור
    0.87
     of
    0.77
    natured
    0.77
    ва
    0.76
    い
    0.75
    Activations Density 0.106%

    No Known Activations