© 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. 55838
    Prev
    Next
    INDEX
    Explanations

    ISO file system

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

    discovering universal 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
     ဖြစ်
    0.55
    𝘃
    0.52
     свого
    0.52
     своїх
    0.51
     молока
    0.50
     বিকেলে
    0.48
     écailles
    0.48
     відповід
    0.47
     soliciting
    0.47
     ізо
    0.47
    POSITIVE LOGITS
    ↵↵
    0.58
    k
    0.54
    arik
    0.53
    lar
    0.52
     Hens
    0.52
     uf
    0.52
     pou
    0.51
    -
    0.51
    ler
    0.50
     meek
    0.50
    Activations Density 0.000%

    No Known Activations