© 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. 54353
    Prev
    Next
    INDEX
    Explanations

    LLC, USAF, USD, EEOC

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

    modifications or excesses

    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
    ỏi
    0.51
    Rồi
    0.47
    疮
    0.46
    iren
    0.46
    saya
    0.46
    জ্
    0.46
    莹
    0.45
    rien
    0.45
    ert
    0.45
    जिंग
    0.45
    POSITIVE LOGITS
     EEOC
    0.50
     Drucker
    0.46
     USD
    0.46
     Lx
    0.45
     LLC
    0.44
     USAF
    0.44
     Kraft
    0.44
     SRAM
    0.44
     և
    0.43
     XD
    0.42
    Activations Density 0.000%

    No Known Activations