© 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. 223648
    Prev
    Next
    INDEX
    Explanations

    discussing various concepts

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

    instructions and questions

    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
    fungsi
    0.48
     konkur
    0.46
     konstit
    0.42
     mycop
    0.42
     wunder
    0.42
    ╼
    0.42
     svare
    0.41
     bintang
    0.41
     hany
    0.40
    ☠
    0.40
    POSITIVE LOGITS
    decrease
    0.48
    রাত
    0.47
     decrease
    0.46
     couvre
    0.44
     이용하여
    0.43
    opposite
    0.43
     overtime
    0.42
     사용하여
    0.42
     involved
    0.42
    মে
    0.42
    Activations Density 0.007%

    No Known Activations