© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 175405
    Prev
    Next
    INDEX
    Explanations

    musical instruments and scientific terms

    np_acts-logits-general · gemini-2.5-flash-lite

    predicting "Aragorn" or "Dr.", word choices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     njegove
    0.48
     عمل
    0.47
    نګه
    0.46
    年后
    0.46
     excepto
    0.45
     except
    0.44
    烷
    0.44
     eso
    0.43
     logotipo
    0.43
    。...
    0.43
    POSITIVE LOGITS
     fréquentes
    0.51
    fed
    0.45
    Schn
    0.44
    c
    0.44
    Notre
    0.44
     Πε
    0.44
     régulièrement
    0.43
    ಿಕ್
    0.43
     Schn
    0.42
     học
    0.42
    Activations Density 0.000%

    No Known Activations