© 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. 98100
    Prev
    Next
    INDEX
    Explanations

    educa or youth related

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

    subject-verb clauses

    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
     Weir
    0.46
     Knut
    0.45
    堑
    0.44
    ("//
    0.44
     Goll
    0.43
     Kj
    0.43
    olius
    0.43
    䊀
    0.43
    ര്‍
    0.42
     Lars
    0.42
    POSITIVE LOGITS
     educa
    0.54
     önces
    0.50
     volupt
    0.45
    EDUC
    0.44
    youth
    0.43
    ああ
    0.43
    డే
    0.42
     pandemic
    0.42
     EDUC
    0.42
    uname
    0.42
    Activations Density 0.000%

    No Known Activations