© 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. 208989
    Prev
    Next
    INDEX
    Explanations

    pressure and website

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

    on-orbit servicing

    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
     תו
    0.52
     މ
    0.50
     معمول
    0.50
     бор
    0.50
     מר
    0.49
     действие
    0.49
     செயல
    0.49
    DateFormat
    0.47
     प्रभावशाली
    0.47
    ூட்
    0.47
    POSITIVE LOGITS
    克的
    0.39
    perturbative
    0.38
    ಿದ್ದೇವೆ
    0.38
    群
    0.37
     CSU
    0.37
     headwinds
    0.37
    伐
    0.37
    زل
    0.37
     dringend
    0.37
     RAND
    0.37
    Activations Density 0.015%

    No Known Activations