© 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. 134946
    Prev
    Next
    INDEX
    Explanations

    phrase / clauses

    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
    ocht
    0.54
     Änder
    0.53
    捙
    0.52
    嵃
    0.50
     পরিবর্তন
    0.50
    fetchAll
    0.49
     AUTHORITY
    0.48
     സ്റ്റ
    0.48
     перемен
    0.47
    perties
    0.47
    POSITIVE LOGITS
    зите
    0.51
    Wise
    0.50
    iran
    0.47
    amo
    0.46
     wise
    0.45
    iel
    0.45
     Wise
    0.44
    bia
    0.44
    3
    0.43
    wise
    0.43
    Activations Density 0.001%

    No Known Activations