© 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. 184046
    Prev
    Next
    INDEX
    Explanations

    placeholders needing replacement

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

    placeholder, TODO, or stub implementation

    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
    abb
    0.41
    叙
    0.41
    改
    0.40
    statistical
    0.38
    回答
    0.38
    Iranian
    0.38
     parton
    0.38
    Iran
    0.38
    <0xAF>
    0.37
    াজী
    0.37
    POSITIVE LOGITS
     ALERT
    0.47
     کنار
    0.47
    보다
    0.46
    tareas
    0.46
     곳
    0.46
     lugar
    0.44
     형태
    0.44
     fırs
    0.44
     estampado
    0.44
     потребности
    0.43
    Activations Density 0.002%

    No Known Activations