© 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. 33420
    Prev
    Next
    INDEX
    Explanations

    start of phrases

    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
     every
    -1.02
     not
    -0.90
    でいい
    -0.85
    voer
    -0.84
     everyone
    -0.83
     your
    -0.83
    вѣ
    -0.79
    嚐
    -0.79
     they
    -0.79
     esquina
    -0.78
    POSITIVE LOGITS
    Wavelength
    0.82
     ۱۳۸
    0.81
     Лей
    0.81
     plundered
    0.80
    endidikan
    0.78
    ocuk
    0.78
     Daimler
    0.78
    ritual
    0.77
    lied
    0.76
     dış
    0.76
    Activations Density 0.000%

    No Known Activations