© 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. 16029
    Prev
    Next
    INDEX
    Explanations

    questions starting with do 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_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
     übrigen
    -1.07
     tepi
    -1.07
     erwähnten
    -1.07
    Étymologie
    -1.06
     мою
    -1.06
     ucap
    -1.05
    owego
    -1.04
     üblichen
    -1.04
    تحميل
    -1.01
    joueurs
    -0.99
    POSITIVE LOGITS
     you
    1.70
    ’
    1.23
     your
    1.22
     Are
    1.20
    ?
    1.19
    //!
    1.18
     have
    1.17
    “
    1.15
     også
    1.14
     want
    1.13
    Activations Density 0.044%

    No Known Activations