© 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. 78923
    Prev
    Next
    INDEX
    Explanations

    error file paths

    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
     manchmal
    -0.82
    ★☆
    -0.79
    }-*/;
    -0.78
    akyti
    -0.77
     épreuve
    -0.77
    レザー
    -0.75
    Минусы
    -0.74
    ächst
    -0.72
    Sometimes
    -0.71
    бище
    -0.71
    POSITIVE LOGITS
     ./
    1.23
     src
    1.13
     file
    1.06
     /
    1.05
     ../
    1.02
    :/
    1.00
    ługość
    0.97
     sources
    0.97
     "/
    0.96
    ../
    0.94
    Activations Density 0.029%

    No Known Activations