© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 52106
    Prev
    Next
    INDEX
    Explanations

    Chinese, Spanish, German, and other international names

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

    collective behavior

    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
    在
    0.46
    過程
    0.44
    три
    0.42
    授
    0.42
     Fortress
    0.41
    ден
    0.41
     things
    0.41
    زن
    0.40
    可谓
    0.40
    次
    0.40
    POSITIVE LOGITS
     அழி
    0.50
    өк
    0.48
     drugih
    0.47
     सहित
    0.46
     रुका
    0.45
    aggia
    0.45
     ऊंचा
    0.45
     Caedwalla
    0.45
     assembled
    0.44
    ı
    0.44
    Activations Density 0.000%

    No Known Activations