© 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. 187155
    Prev
    Next
    INDEX
    Explanations

    pets, failure, calls, evolving

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

    Predicting or defining functions

    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
    Negative Logits
     всех
    0.49
     probed
    0.48
    鋲
    0.47
     усіх
    0.47
    𝖑
    0.47
     \%$
    0.44
    cyl
    0.44
    מיני
    0.44
     бук
    0.43
    マルチ
    0.43
    POSITIVE LOGITS
    Ậ
    0.46
    を踏
    0.46
    ocardi
    0.45
     العلوم
    0.45
     Proced
    0.45
     Methods
    0.44
    Proced
    0.43
    ا
    0.43
     روش
    0.43
     gestures
    0.43
    Activations Density 0.000%

    No Known Activations