© 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. 163048
    Prev
    Next
    INDEX
    Explanations

    cleanup problems and lists

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

    random encounters

    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
     ჩვენ
    0.52
     navigateur
    0.47
     promove
    0.47
     péld
    0.47
     panneaux
    0.47
     poesia
    0.46
     reconnaît
    0.46
    𝖊
    0.46
     zwięks
    0.46
     Stefan
    0.45
    POSITIVE LOGITS
     victims
    0.49
    selected
    0.47
    解析
    0.44
    ösungen
    0.44
     injuries
    0.44
     culprits
    0.44
    örungen
    0.44
    result
    0.44
    веро
    0.43
     발생하는
    0.43
    Activations Density 0.001%

    No Known Activations