© 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. 30295
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
     obtained
    -1.12
     obtain
    -0.94
     obtaining
    -0.85
     Obtained
    -0.83
    obtained
    -0.81
     obtainable
    -0.80
     Obtain
    -0.78
    obtain
    -0.77
     Obtaining
    -0.77
     Heimat
    -0.75
    POSITIVE LOGITS
    Seeker
    0.77
     رسم
    0.73
    Kons
    0.72
    Knot
    0.71
     בת
    0.69
     раск
    0.68
    tiga
    0.68
     Bertie
    0.68
     GE
    0.67
    辞
    0.67
    Activations Density 0.016%

    No Known Activations