© 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. 115010
    Prev
    Next
    INDEX
    Explanations

    people, places, and things

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

    continued across Japanese culture

    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
     Story
    0.43
     JAVA
    0.42
     ADA
    0.41
     Antibody
    0.41
     LinkedIn
    0.40
     Achieving
    0.40
     EGFR
    0.40
    𝟰
    0.40
     aspetti
    0.39
     Creo
    0.39
    POSITIVE LOGITS
     remorse
    0.51
    चारी
    0.48
     перед
    0.48
     вызыва
    0.47
    ের
    0.46
     repose
    0.46
     உத்தர
    0.45
     메서
    0.44
     நே
    0.43
    lassen
    0.43
    Activations Density 0.001%

    No Known Activations