© 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. 128138
    Prev
    Next
    INDEX
    Explanations

    questions asking why

    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
     asistencia
    -0.89
    Historie
    -0.88
     ajan
    -0.87
    zeć
    -0.86
     lagar
    -0.84
     quæ
    -0.84
     padang
    -0.83
    tbx
    -0.83
    朱印
    -0.82
    惑星
    -0.82
    POSITIVE LOGITS
     Explain
    1.43
    Explain
    1.17
     explain
    1.14
     Why
    1.10
     why
    1.07
     and
    1.06
     क्यों
    1.05
    Why
    1.03
     reason
    1.02
     your
    0.99
    Activations Density 0.066%

    No Known Activations