© 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. 21006
    Prev
    Next
    INDEX
    Explanations

    perfect if, able to, improve efficiency, concrete forms

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

    core, Blocks, return

    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
     عنه
    0.48
     cyclists
    0.47
     entrepreneurs
    0.46
     anticipate
    0.45
    kwargs
    0.45
    ⌐
    0.45
     anticipates
    0.44
     bystanders
    0.44
    洸
    0.44
     dxc
    0.43
    POSITIVE LOGITS
    an
    0.47
    ită
    0.47
    신의
    0.47
     Service
    0.46
    ก
    0.45
    alinga
    0.43
    oit
    0.42
    ação
    0.42
     Saint
    0.42
     Siz
    0.41
    Activations Density 0.001%

    No Known Activations