© 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. 22-GEMMASCOPE-RES-131K
    7. 72915
    Prev
    Next
    INDEX
    Explanations

    cause or responsibility for

    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_22/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
     until
    -1.30
    と思っていた
    -1.16
    かなぁ
    -1.11
     drunkenness
    -1.04
     forgery
    -0.96
    釆
    -0.95
    というと
    -0.95
     different
    -0.95
    '];
    -0.94
    layoutControl
    -0.92
    POSITIVE LOGITS
    ícias
    1.44
    此次
    1.36
     美丽
    1.24
     why
    1.20
    praxis
    1.20
     considérons
    1.16
     estimés
    1.14
    这次
    1.09
    bluza
    1.09
     schuld
    1.07
    Activations Density 0.050%

    No Known Activations