© 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. 2752
    Prev
    Next
    INDEX
    Explanations

    copyright notices

    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
     nhiều
    -0.81
    ことができ
    -0.75
     Spanish
    -0.68
    為に
    -0.68
    いてる
    -0.66
    ResponseData
    -0.66
     matric
    -0.65
    OnTop
    -0.65
     haue
    -0.65
    Dum
    -0.65
    POSITIVE LOGITS
     Ith
    0.65
    处理
    0.65
    eliminar
    0.64
     Handling
    0.64
     Begle
    0.63
    麒
    0.62
     Syed
    0.62
     solches
    0.62
     छा
    0.61
    roles
    0.61
    Activations Density 0.079%

    No Known Activations