© 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. 10-GEMMASCOPE-RES-131K
    7. 101429
    Prev
    Next
    INDEX
    Explanations

    have you

    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_10/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
     ALUMIN
    -1.71
     MINERAL
    -1.65
     PROFESSOR
    -1.65
    👎
    -1.63
     LECTURE
    -1.63
    感觉到
    -1.63
     RAILWAY
    -1.63
    ﮨ
    -1.62
     ROBER
    -1.60
     CARLOS
    -1.60
    POSITIVE LOGITS
     been
    2.59
     you
    2.27
    ing
    1.88
    nt
    1.80
    4
    1.68
    5
    1.66
     of
    1.63
     Could
    1.61
     it
    1.57
     et
    1.55
    Activations Density 0.010%

    No Known Activations