© 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. 6057
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

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

    a 6 Goblin cow

    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
     नकार
    0.38
    𠃍
    0.37
    roveň
    0.33
    㞒
    0.32
    kannt
    0.30
     durchaus
    0.30
     widers
    0.30
     অজ্ঞ
    0.30
    stantial
    0.30
    ες
    0.30
    POSITIVE LOGITS
    פ
    0.36
    Android
    0.32
     Digital
    0.32
     Music
    0.32
     FPGA
    0.32
    Audio
    0.31
    Game
    0.31
    Gu
    0.30
    الم
    0.30
    Music
    0.30
    Activations Density 0.169%

    No Known Activations