© 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. 105396
    Prev
    Next
    INDEX
    Explanations

    mechanics of, file, involves

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

    while clauses

    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
     একখানি
    0.50
    SERVICIO
    0.50
    nä
    0.49
    СТ
    0.49
    ТР
    0.49
    ESSITY
    0.49
     янва
    0.48
     チ
    0.48
    
    0.46
     FAILURE
    0.46
    POSITIVE LOGITS
     présent
    0.52
    ություններ
    0.45
    方式
    0.44
     eventual
    0.44
    พื้น
    0.44
    osur
    0.43
     on
    0.43
    ències
    0.42
     across
    0.42
    顺
    0.42
    Activations Density 0.000%

    No Known Activations