© 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. 73139
    Prev
    Next
    INDEX
    Explanations

    ratings and estimates

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

    specifications and details

    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
    ↵↵
    0.61
    ↵
    0.57
     in
    0.54
     VMs
    0.53
     res
    0.53
     maybe
    0.53
     EVs
    0.53
     you
    0.52
     can
    0.51
     +
    0.51
    POSITIVE LOGITS
    俄罗斯
    0.52
    サラ
    0.51
    適用
    0.49
    涉及
    0.49
    溲
    0.49
    统一
    0.48
    กรา
    0.48
    颜
    0.48
    适用于
    0.48
    硅
    0.48
    Activations Density 0.000%

    No Known Activations