© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 11939
    Prev
    Next
    INDEX
    Explanations

    whom we/you

    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
    IN
    0.53
     భాగంగా
    0.53
     melibatkan
    0.50
    a
    0.50
    া
    0.49
    ।"
    0.48
    ড
    0.46
    inį
    0.45
     بیٹے
    0.44
     এলাক
    0.44
    POSITIVE LOGITS
    soever
    0.62
     we
    0.54
    é
    0.47
     cui
    0.46
     можно
    0.45
     можна
    0.45
    ми
    0.45
     också
    0.44
    有一些
    0.44
     you
    0.44
    Activations Density 0.005%

    No Known Activations