© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110687
    Prev
    Next
    INDEX
    Explanations

    asking or selling

    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
    nadequate
    -1.26
     régal
    -1.04
    ándonos
    -0.98
    carus
    -0.98
     szerint
    -0.97
    ویت
    -0.95
    我們
    -0.94
    Ḵ
    -0.94
    írit
    -0.94
    īt
    -0.94
    POSITIVE LOGITS
     asking
    1.79
     comes
    1.63
     selling
    1.63
     Asking
    1.54
     willing
    1.51
    Asking
    1.29
     interested
    1.29
     please
    1.27
     requesting
    1.26
     looking
    1.24
    Activations Density 0.011%

    No Known Activations