© 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. 169636
    Prev
    Next
    INDEX
    Explanations

    monitor progress

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

    current status and ongoing tasks

    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
    нус
    0.54
     addicts
    0.53
    硬件
    0.49
     railings
    0.48
     sidewalks
    0.46
     exporters
    0.46
     anglers
    0.46
    댔
    0.45
    њу
    0.45
     bicyclists
    0.44
    POSITIVE LOGITS
    strnc
    0.54
    rot
    0.46
    ijd
    0.44
    waan
    0.44
    vala
    0.44
     সোশ্যাল
    0.43
    atka
    0.43
    基本的な
    0.43
    convers
    0.42
    th
    0.42
    Activations Density 0.001%

    No Known Activations