© 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. 117515
    Prev
    Next
    INDEX
    Explanations

    script libs and document titles

    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
    鄄
    -0.71
     originator
    -0.63
     berfungsi
    -0.63
    домо
    -0.63
     Đường
    -0.62
     tpu
    -0.62
    findBy
    -0.62
    CIRCLE
    -0.62
    nerie
    -0.62
    いますが
    -0.62
    POSITIVE LOGITS
    шту
    0.75
     miếng
    0.71
    ('_
    0.69
    Award
    0.68
    Disposable
    0.68
    Pour
    0.67
    Arg
    0.67
    英国
    0.66
    tsz
    0.66
    еро
    0.65
    Activations Density 0.049%

    No Known Activations