© 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. 57294
    Prev
    Next
    INDEX
    Explanations

    project, politics, license, fork

    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
     gr
    -0.77
    ised
    -0.72
    ted
    -0.71
     cyclic
    -0.71
    ley
    -0.70
    pr
    -0.69
     spars
    -0.68
    ีย์
    -0.68
    bst
    -0.67
     stuff
    -0.66
    POSITIVE LOGITS
     酱
    0.85
    ꇴ
    0.81
    PRODU
    0.80
    papar
    0.78
    Sey
    0.78
     尼
    0.78
    ◸
    0.77
    extreme
    0.77
    eaza
    0.77
     fredag
    0.76
    Activations Density 0.225%

    No Known Activations