© 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. 145155
    Prev
    Next
    INDEX
    Explanations

    after detectingthick stacksor file

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

    languages, volumes, personalities, Window

    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
     (
    0.50
    t
    0.47
    e
    0.46
    an
    0.45
     '
    0.45
    ren
    0.45
     tess
    0.44
     be
    0.43
    ian
    0.43
     ,
    0.43
    POSITIVE LOGITS
    ᱕
    0.53
    াড়া
    0.51
    openapi
    0.51
    開催
    0.51
    =\{
    0.51
     требований
    0.51
     nhất
    0.50
    szág
    0.50
     мальчика
    0.50
    ὦ
    0.50
    Activations Density 0.001%

    No Known Activations