© 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. 34397
    Prev
    Next
    INDEX
    Explanations

    common nouns and specific terms

    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
     zudem
    -1.11
    Might
    -1.03
     however
    -1.02
     MIGHT
    -0.98
    might
    -0.98
     vermutlich
    -0.96
     zuhause
    -0.93
     anstatt
    -0.92
     might
    -0.91
    con
    -0.89
    POSITIVE LOGITS
    ⏜
    1.13
     clerk
    1.09
    хані
    1.06
     voltaje
    0.95
    ofag
    0.94
     revisar
    0.93
    sudadera
    0.92
    Sagittarius
    0.92
    avocado
    0.91
    ⠊
    0.91
    Activations Density 0.049%

    No Known Activations