© 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. 151953
    Prev
    Next
    INDEX
    Explanations

    Northern and Southern hemispheres

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

    end of phrases

    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
    ɣ
    0.55
     resurrected
    0.50
     rediscovered
    0.48
    aln
    0.48
     powdered
    0.47
     pigmented
    0.47
     equilibrated
    0.47
     phal
    0.46
     gau
    0.46
     wrinkled
    0.46
    POSITIVE LOGITS
    萜
    0.54
    㕷
    0.52
    倔
    0.50
    тік
    0.50
    ها
    0.47
    ITÉ
    0.47
    损失
    0.47
    тері
    0.47
     Wärme
    0.47
     Müller
    0.46
    Activations Density 0.000%

    No Known Activations