© 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. 197235
    Prev
    Next
    INDEX
    Explanations

    God via

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

    human endeavors and abstract concepts

    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
    KI
    0.47
    降
    0.46
    Kü
    0.45
    Of
    0.45
    
    0.43
    探
    0.42
    H
    0.42
    ogg
    0.41
    Cu
    0.41
    ú
    0.40
    POSITIVE LOGITS
    मार्ग
    0.60
     بالوں
    0.60
     felon
    0.56
     graduates
    0.50
     vernacular
    0.47
    gruntled
    0.47
    ValueLayout
    0.47
     maintien
    0.47
     manual
    0.46
     bilingual
    0.46
    Activations Density 0.000%

    No Known Activations