© 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. 175646
    Prev
    Next
    INDEX
    Explanations

    post information

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

    surgery, replace, sword, product, button

    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
     kttt
    0.49
    풋
    0.49
    呑
    0.48
     আন্দোল
    0.47
     необхідно
    0.46
     bairro
    0.46
    ビック
    0.46
     It
    0.45
    大きさ
    0.44
    чны
    0.44
    POSITIVE LOGITS
    ，
    0.47
     {\
    0.45
     or
    0.44
     before
    0.43
     或
    0.43
    কোনও
    0.43
    。
    0.43
    或者
    0.43
     અથવા
    0.42
    ።
    0.42
    Activations Density 0.000%

    No Known Activations