© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71226
    Prev
    Next
    INDEX
    Explanations

    still in progress

    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
    ")));
    -0.97
    mayan
    -0.85
    Attempts
    -0.84
     also
    -0.83
     "!
    -0.82
     دے
    -0.82
     lẽ
    -0.82
     ...........
    -0.81
    굽
    -0.79
     royaume
    -0.77
    POSITIVE LOGITS
     until
    1.87
     هنوز
    1.59
    はまだ
    1.55
     अभी
    1.55
     ainda
    1.55
     dopiero
    1.54
     yet
    1.52
     belum
    1.47
    まだ
    1.45
    还没有
    1.45
    Activations Density 0.027%

    No Known Activations