© 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. 172872
    Prev
    Next
    INDEX
    Explanations

    team providing services

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

    quick access remote recipe

    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
     endereco
    0.46
    MODULE
    0.46
     credential
    0.46
    AGENT
    0.46
    ikka
    0.43
    MAJOR
    0.43
    গুপ্ত
    0.43
    㬶
    0.43
    店
    0.43
     BELOW
    0.42
    POSITIVE LOGITS
    காற்று
    0.50
     எளி
    0.48
     hampir
    0.48
     Nhân
    0.47
     почти
    0.44
     raisin
    0.44
     अमाव
    0.44
     இயற்க
    0.44
     صاف
    0.43
     ശു
    0.43
    Activations Density 0.000%

    No Known Activations