© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 246552
    Prev
    Next
    INDEX
    Explanations

    updated examination materials

    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
    Მ
    0.46
     వీరి
    0.44
    氳
    0.43
    akum
    0.42
    মিও
    0.41
    ৪৮
    0.41
    ঠোর
    0.41
    மக்கள்
    0.40
    мян
    0.40
    ઠવા
    0.40
    POSITIVE LOGITS
     |
    0.41
     >
    0.39
     sputtering
    0.37
     actualizado
    0.36
     Doctoral
    0.36
     modulate
    0.36
     healthful
    0.36
     admirable
    0.36
     Hersteller
    0.35
     RoHS
    0.35
    Activations Density 0.000%

    No Known Activations