© 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. 34-GEMMASCOPE-RES-131K
    7. 3293
    Prev
    Next
    INDEX
    Explanations

    could want ask need

    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_34/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
     Able
    -0.91
    MatButtonModule
    -0.88
    Able
    -0.84
     BAND
    -0.79
    ABLE
    -0.78
     мысль
    -0.77
    HET
    -0.77
     す
    -0.77
    容易
    -0.75
     Pion
    -0.73
    POSITIVE LOGITS
     hoped
    1.80
     ask
    1.80
     asked
    1.80
     asks
    1.77
     hope
    1.72
     wished
    1.53
     wish
    1.53
     asking
    1.46
     Ask
    1.39
    ask
    1.38
    Activations Density 0.016%

    No Known Activations