© 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. 216594
    Prev
    Next
    INDEX
    Explanations

    front or back graphics

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

    future collectibles

    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
     intercalation
    0.55
    p
    0.50
    k
    0.49
    l
    0.47
     Thus
    0.46
     fatten
    0.46
     greed
    0.44
    a
    0.44
     inorder
    0.43
    an
    0.43
    POSITIVE LOGITS
     യുവാ
    0.55
    地域の
    0.55
     бюд
    0.54
     نہيں
    0.54
    <unused47>
    0.54
     સ્થાન
    0.54
     শিক্ষকদের
    0.52
     университе
    0.52
     universidades
    0.51
     হাস
    0.51
    Activations Density 0.000%

    No Known Activations