© 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. 17124
    Prev
    Next
    INDEX
    Explanations

    study notes and 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
    ת
    0.49
    ли
    0.44
    膣
    0.42
    тю
    0.41
    व्
    0.40
    selfish
    0.40
     breast
    0.40
    বাহিনী
    0.40
    aworld
    0.40
    awed
    0.40
    POSITIVE LOGITS
     نمبر
    0.48
    Tokenizer
    0.45
     ponctué
    0.44
     Partie
    0.43
     وقد
    0.43
    편
    0.42
     RESPON
    0.42
     Erfol
    0.41
    诏
    0.41
     CORPER
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.