© 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. 32042
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific entities

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

    ss command usage

    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
     imparted
    0.50
     varieties
    0.46
    "
    0.45
    ревно
    0.44
     Jacoby
    0.43
     Varieties
    0.42
     руба
    0.42
     `${
    0.41
     apportion
    0.41
    रूप
    0.41
    POSITIVE LOGITS
     otw
    0.53
     protokol
    0.52
     funkce
    0.52
    Tun
    0.51
    şt
    0.49
     சுண்ணா
    0.49
     lös
    0.49
     dată
    0.49
     okam
    0.48
    endige
    0.48
    Activations Density 0.000%

    No Known Activations