© 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. 84915
    Prev
    Next
    INDEX
    Explanations

    hazard signs, counties, singing

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

    bone fragmentation

    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
    gpg
    0.45
    ӟ
    0.44
    ópolis
    0.44
    泊
    0.43
    ږئ
    0.43
    processes
    0.43
    november
    0.43
    geek
    0.43
    쉰
    0.42
    قيم
    0.42
    POSITIVE LOGITS
     आवाज
    0.54
     развивается
    0.54
     cheveux
    0.52
     живота
    0.49
     voix
    0.47
     እንኳን
    0.47
     a
    0.46
    யில்
    0.46
     curtain
    0.46
     Pham
    0.45
    Activations Density 0.001%

    No Known Activations