© 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. 23401
    Prev
    Next
    INDEX
    Explanations

    multicellular and scientific terms

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

    stopped, unresponsive, or broken state

    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
     fiori
    0.46
     Gnome
    0.45
     lại
    0.44
     dźwię
    0.44
    又
    0.44
     IPC
    0.42
    frames
    0.41
     নিয়ম
    0.41
    flow
    0.41
    ి
    0.41
    POSITIVE LOGITS
    ostatistics
    0.47
     ಭಾಗ
    0.46
    は大
    0.45
    opoietic
    0.45
     بخش
    0.44
    Agricultural
    0.44
    istem
    0.44
    inally
    0.44
    ufficient
    0.43
    oblast
    0.43
    Activations Density 0.000%

    No Known Activations