© 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. 141911
    Prev
    Next
    INDEX
    Explanations

    gift box, court pronounced, temporary pain

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

    companies and group

    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
    sembling
    0.58
    EndTime
    0.52
    r
    0.52
    g
    0.52
    ر
    0.52
    মন্ত্রী
    0.52
     CreateWindow
    0.51
    wj
    0.49
    d
    0.49
     ಮಾಡಿ
    0.49
    POSITIVE LOGITS
     trocar
    0.52
     fuerza
    0.51
     adiab
    0.49
     meilleur
    0.48
     splice
    0.48
     descent
    0.47
     conex
    0.47
     rud
    0.47
     deck
    0.47
     abord
    0.47
    Activations Density 0.000%

    No Known Activations