© 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. 15923
    Prev
    Next
    INDEX
    Explanations

    address decoder, data packets, RS pin, voltage regulator, select button

    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
     \%$
    -1.24
     you
    -1.20
     in
    -1.20
    </em>
    -1.20
    氏
    -1.13
     no
    -1.11
    I
    -1.11
    éfonos
    -1.08
    szön
    -1.08
    世界的
    -1.07
    POSITIVE LOGITS
    了几
    1.52
     getestet
    1.50
    ⟢
    1.30
    Legenda
    1.26
    Елена
    1.25
    ஊ
    1.25
    podr
    1.23
     colorear
    1.21
    szám
    1.20
    Kontra
    1.19
    Activations Density 0.001%

    No Known Activations