© 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. 237875
    Prev
    Next
    INDEX
    Explanations

    may revoke, liability of, read notice

    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
     finanz
    0.51
     entstehen
    0.48
    감독
    0.46
    لينكات
    0.45
    बिहार
    0.44
    Leben
    0.44
    ⴳ
    0.44
    る
    0.43
    腥
    0.43
     naciones
    0.42
    POSITIVE LOGITS
     June
    0.50
     August
    0.49
     October
    0.48
     switched
    0.48
     February
    0.47
     বিকল্প
    0.46
     อาจารย์
    0.46
     Instructor
    0.45
     Shou
    0.44
     impossible
    0.44
    Activations Density 0.001%

    No Known Activations