© 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. 114792
    Prev
    Next
    INDEX
    Explanations

    quantitative measurements

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

    composition API and principles

    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
     husbands
    0.46
     sparsebundle
    0.45
     prijatel
    0.44
     castration
    0.44
    िप
    0.43
     комна
    0.42
    贛
    0.42
    тур
    0.42
    сол
    0.42
     पार्वती
    0.41
    POSITIVE LOGITS
     থাকবে
    0.54
     才
    0.53
     interessante
    0.51
     Mapping
    0.50
     Rober
    0.49
     Woche
    0.49
    percent
    0.48
    month
    0.47
     還
    0.47
    quantitative
    0.47
    Activations Density 0.000%

    No Known Activations