© 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. 78499
    Prev
    Next
    INDEX
    Explanations

    following `»`

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

    abiotic factors

    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
    ಪ
    0.52
    C
    0.48
    Z
    0.47
    О
    0.46
    ㄆ
    0.46
    SDLCheck
    0.45
    مد
    0.45
    Republican
    0.45
    ㄎ
    0.44
    Ö
    0.44
    POSITIVE LOGITS
     pollinators
    0.53
     którzy
    0.50
     quienes
    0.50
     herbivores
    0.49
     আশেপাশে
    0.48
    িং
    0.48
     ისინი
    0.46
     actividad
    0.46
     ними
    0.46
     existentes
    0.45
    Activations Density 0.001%

    No Known Activations