© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 136259
    Prev
    Next
    INDEX
    Explanations

    actions, queries, and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     diminue
    0.50
    ծ
    0.48
    рия
    0.46
     sullen
    0.45
     обоих
    0.45
    jecture
    0.45
     diminish
    0.45
     fixa
    0.45
     peu
    0.44
     ρ
    0.44
    POSITIVE LOGITS
    钢琴
    0.47
    o
    0.42
     prosecutions
    0.42
    //
    0.40
    ["
    0.40
    播放
    0.40
    语义
    0.39
    名
    0.39
     Bulb
    0.39
    CameraOpened
    0.38
    Activations Density 0.002%

    No Known Activations