© 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. 248111
    Prev
    Next
    INDEX
    Explanations

    common contextual words

    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
    ಮಾ
    0.42
     clearContext
    0.42
     письма
    0.41
    reflectionCamera
    0.40
    本科
    0.40
    toISOString
    0.39
    
    0.39
    Session
    0.38
     церков
    0.38
     occasioned
    0.38
    POSITIVE LOGITS
     etn
    0.52
    7
    0.51
     selatan
    0.51
    5
    0.50
     apoy
    0.50
     spaz
    0.50
     Mbappe
    0.49
     Vielzahl
    0.49
     quinze
    0.49
     carros
    0.48
    Activations Density 0.001%

    No Known Activations