© 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. 128895
    Prev
    Next
    INDEX
    Explanations

    sensitive information or copyright

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

    interior lunar studies

    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
    م
    0.51
     还
    0.46
     они
    0.44
    tener
    0.43
    蚁
    0.43
    té
    0.43
     Aquí
    0.43
    منا
    0.42
    dmg
    0.42
     đầy
    0.42
    POSITIVE LOGITS
    ør
    0.50
    chnitten
    0.49
    ä
    0.48
    ワンピース
    0.47
    וף
    0.47
    Conventional
    0.47
    ö
    0.46
    Ø
    0.46
    哼
    0.46
     snoring
    0.45
    Activations Density 0.000%

    No Known Activations