© 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. 30990
    Prev
    Next
    INDEX
    Explanations

    function arguments

    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
     distanza
    -0.91
    VertexAttrib
    -0.82
    を
    -0.80
     applic
    -0.80
     mobilya
    -0.80
    編曲
    -0.78
     Genuine
    -0.76
     misma
    -0.75
     traduc
    -0.75
    歌詞
    -0.74
    POSITIVE LOGITS
    %%%%%%%
    1.09
     maneras
    1.06
     отдела
    0.94
     adequado
    0.93
     webinars
    0.92
    虢
    0.90
     reposo
    0.89
    intos
    0.89
     pés
    0.88
    ॄ
    0.88
    Activations Density 0.116%

    No Known Activations