© 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. 4051
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    apol
    0.63
    ospital
    0.54
    ikar
    0.53
    av
    0.52
    ik
    0.50
    \)
    0.49
    ikul
    0.49
    }
    0.48
    ak
    0.47
    ikl
    0.47
    POSITIVE LOGITS
     improvisation
    0.50
    जे
    0.50
    SPREAD
    0.48
    вый
    0.47
     suggestions
    0.47
     自動
    0.47
     느낌
    0.46
     meditations
    0.46
    वाना
    0.45
     interaction
    0.45
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.