© 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. 169612
    Prev
    Next
    INDEX
    Explanations

    Funnels that

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

    discriminating algorithms

    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
    ier
    0.46
    さんが
    0.46
     qualifying
    0.44
     battle
    0.43
     semblance
    0.43
    et
    0.43
    Ｕ
    0.43
     roundabout
    0.43
     ambush
    0.42
     $
    0.41
    POSITIVE LOGITS
    maları
    0.52
     estructuras
    0.50
     струк
    0.50
    whether
    0.50
     বিষয়ে
    0.49
    нил
    0.48
     ලි
    0.47
    asını
    0.47
     ယ
    0.47
    RetResult
    0.46
    Activations Density 0.001%

    No Known Activations