© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 35255
    Prev
    Next
    INDEX
    Explanations

    next week

    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_16_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
    يه
    0.88
    ن
    0.88
    nél
    0.87
    大
    0.87
    فيد
    0.75
    이랑
    0.75
    ر
    0.74
    ونکي
    0.74
    li
    0.73
    nione
    0.73
    POSITIVE LOGITS
    '
    1.20
    akes
    0.91
    ANG
    0.82
    ↵↵
    0.80
    df
    0.80
    EN
    0.78
    .'
    0.78
    ER
    0.77
    ire
    0.76
    ives
    0.75
    Activations Density 0.005%

    No Known Activations