© 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. 25821
    Prev
    Next
    INDEX
    Explanations

    technical descriptions and code

    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
     to
    -1.18
     rano
    -1.08
     krim
    -1.06
     umo
    -1.02
     testSet
    -1.02
     nifer
    -1.01
    rhos
    -1.00
     hefyd
    -0.99
     boya
    -0.99
    任何
    -0.98
    POSITIVE LOGITS
     kathol
    1.29
    ()]
    1.20
    Bibliografie
    1.17
    SafeAreaView
    1.16
     problemas
    1.15
     τὸν
    1.14
     atento
    1.10
    Thông
    1.09
     arrancar
    1.08
     начать
    1.07
    Activations Density 0.002%

    No Known Activations