© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 187832
    Prev
    Next
    INDEX
    Explanations

    easier escalation

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

    syntax editor programming

    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
     المره
    0.47
    𝚐
    0.47
     gelten
    0.46
     كانوا
    0.44
    liefer
    0.44
     Expend
    0.43
    abbani
    0.43
     obliv
    0.43
     aggrieved
    0.43
    ataire
    0.42
    POSITIVE LOGITS
    Joshua
    0.43
    ایل
    0.42
    ()),
    0.41
    帯
    0.41
    を使用した
    0.39
    னோ
    0.39
     hutan
    0.38
    の問題
    0.38
     để
    0.38
     fumar
    0.38
    Activations Density 0.001%

    No Known Activations