© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117658
    Prev
    Next
    INDEX
    Explanations

    cleanup and reset operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     插入
    -0.77
     Você
    -0.76
     Within
    -0.74
    risti
    -0.74
    ꯕ
    -0.73
    Aprend
    -0.73
    Faj
    -0.72
    }}}
    -0.72
    /");
    -0.71
     contemporaries
    -0.70
    POSITIVE LOGITS
    resources
    1.03
     resources
    1.00
    ➪
    0.97
    เคย
    0.92
    Linear
    0.89
    資源
    0.86
     valoración
    0.79
     interviewer
    0.78
    urium
    0.77
     किसी
    0.77
    Activations Density 0.002%

    No Known Activations