© 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. 201690
    Prev
    Next
    INDEX
    Explanations

    Generate button

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

    illustrations, telegram, wasting

    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
    ن
    0.51
    真实的
    0.50
     वास्तविकता
    0.48
    เต
    0.47
     eigent
    0.46
    ímenes
    0.46
     tenacity
    0.45
     विविध
    0.44
    恸
    0.43
    eness
    0.43
    POSITIVE LOGITS
     medicine
    0.48
     Ken
    0.47
     Medicine
    0.47
     riun
    0.46
     Marlin
    0.44
     Mun
    0.44
     Tob
    0.44
     Ml
    0.44
     Clyde
    0.43
     Monro
    0.43
    Activations Density 0.000%

    No Known Activations