© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99538
    Prev
    Next
    INDEX
    Explanations

    names and places

    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
    şa
    -0.81
    が
    -0.78
    стай
    -0.75
     लगभग
    -0.74
    iją
    -0.74
    郑州
    -0.73
    子が
    -0.72
    と
    -0.72
    それは
    -0.71
     bếp
    -0.71
    POSITIVE LOGITS
     自転車
    0.99
    ことができ
    0.93
    ができます
    0.90
    必要があります
    0.88
    >";
    0.88
    こともあり
    0.86
    ivez
    0.85
    場合があります
    0.85
    acab
    0.83
     リュック
    0.83
    Activations Density 0.031%

    No Known Activations