© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 94450
    Prev
    Next
    INDEX
    Explanations

    Ltd. nurses offering chance found

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

    generating explanations or descriptions

    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
    Negative Logits
     見
    0.51
    ழ்ச்ச
    0.50
     manoe
    0.50
     ۋ
    0.48
     высо
    0.48
     agacch
    0.47
     инстру
    0.46
     rhinophores
    0.46
    𝐯
    0.46
     высоте
    0.44
    POSITIVE LOGITS
     can
    0.47
    ামূলক
    0.46
    Overflow
    0.44
     generate
    0.44
     Generating
    0.44
     sudo
    0.44
     Generate
    0.43
     Blackwell
    0.43
     Commitment
    0.42
    에
    0.42
    Activations Density 0.002%

    No Known Activations