© 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. 123440
    Prev
    Next
    INDEX
    Explanations

    training physicians

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

    verb or adverb followed by "to" or phrase

    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
    fu
    0.43
    𝗆
    0.43
    ers
    0.41
    ji
    0.41
    مع
    0.41
    使
    0.40
    []>
    0.40
    ศิลป
    0.40
    tl
    0.40
     morphological
    0.40
    POSITIVE LOGITS
     ngunit
    0.46
     ولكن
    0.46
     ghế
    0.45
     નક્
    0.44
     tetapi
    0.43
     Joon
    0.43
     */;
    0.43
     pero
    0.42
     असताना
    0.42
     appena
    0.42
    Activations Density 0.002%

    No Known Activations