© 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. 13406
    Prev
    Next
    INDEX
    Explanations

    this page, 06, from teaching

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

    cryptography

    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
     கெல்வின்
    0.45
     பின்பற்ற
    0.44
    verd
    0.44
    gaan
    0.44
     पांव
    0.43
     উত্থ
    0.43
    elink
    0.42
    讃
    0.42
     Bestand
    0.41
     chuan
    0.41
    POSITIVE LOGITS
    ع
    0.60
    โย
    0.53
    ྲ
    0.52
     sk
    0.50
    ตร
    0.50
    น
    0.48
    ോഷ്യ
    0.47
    โซ
    0.47
     submodule
    0.46
     tr
    0.45
    Activations Density 0.000%

    No Known Activations