© 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. 31490
    Prev
    Next
    INDEX
    Explanations

    reflect the, LOST THIS, CC means

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

    officer, Code, nutrients, Facebook

    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
    poser
    0.44
    絴
    0.43
    stmt
    0.43
    ,\"
    0.43
     Transforms
    0.42
    ಿಸಿದ್ದರು
    0.42
     scienze
    0.41
    雵
    0.41
     amounted
    0.41
    atii
    0.41
    POSITIVE LOGITS
    Chúc
    0.45
    のため
    0.43
     hảo
    0.41
     chính
    0.41
    が悪
    0.40
    というのが
    0.39
    の下
    0.39
     Abyss
    0.39
     random
    0.39
    一切
    0.39
    Activations Density 0.000%

    No Known Activations