© 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. 15506
    Prev
    Next
    INDEX
    Explanations

    Whether you're looking

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

    years, lesion, Superset

    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
    тельство
    0.36
     ru
    0.35
     confirmed
    0.35
     OnInit
    0.35
    <0xBC>
    0.34
     Streak
    0.33
     orchestrated
    0.33
     of
    0.33
    Ф
    0.33
     Vell
    0.32
    POSITIVE LOGITS
    ulsory
    0.40
    idać
    0.39
    下一个
    0.39
     उसी
    0.39
    capitalize
    0.39
    tls
    0.38
    illä
    0.38
    spor
    0.37
     ಮುಂದ
    0.37
     damal
    0.37
    Activations Density 0.000%

    No Known Activations