© 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. 178069
    Prev
    Next
    INDEX
    Explanations

    traditional Mexican songs and wolves

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

    date and time handling

    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
    Ру
    0.45
    Fin
    0.44
     Ру
    0.44
    getY
    0.44
    的
    0.43
    没有
    0.43
     allong
    0.42
    의
    0.42
    Function
    0.42
    низу
    0.41
    POSITIVE LOGITS
     ಆದ್ದರಿಂದ
    0.50
     売
    0.44
     しかし
    0.43
     आढा
    0.43
    ایید
    0.43
    輋
    0.42
     રાશિફળ
    0.42
     ikut
    0.41
     सध्या
    0.41
     தடை
    0.41
    Activations Density 0.000%

    No Known Activations