© 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. 65405
    Prev
    Next
    INDEX
    Explanations

    starts of words/proper nouns

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

    py/hy/sy prefixes followed by text

    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
    n
    0.94
    miş
    0.91
    nál
    0.84
    ാ
    0.82
    nél
    0.80
    ية
    0.80
    ാത്ത
    0.79
    l
    0.76
    nisse
    0.75
     Samaritan
    0.73
    POSITIVE LOGITS
    는
    0.98
    .
    0.97
     was
    0.86
    0
    0.84
    は
    0.82
     был
    0.81
     був
    0.80
     бя
    0.79
     về
    0.77
    ۔
    0.76
    Activations Density 0.258%

    No Known Activations