© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 29626
    Prev
    Next
    INDEX
    Explanations

    pocket and compartments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ᾧ
    0.46
     Bake
    0.46
     Jeux
    0.44
     Schaus
    0.44
    ಋ
    0.43
     Haft
    0.43
     ஜூ
    0.43
    騏
    0.42
     Karate
    0.42
     Ша
    0.41
    POSITIVE LOGITS
     pocket
    0.97
    Pocket
    0.88
     pockets
    0.86
    pocket
    0.84
     Pocket
    0.81
     जेब
    0.77
    ポケット
    0.69
     bolsillo
    0.68
    口袋
    0.67
     pouch
    0.67
    Activations Density 0.010%

    No Known Activations