© 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. 151254
    Prev
    Next
    INDEX
    Explanations

    group or team context

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

    mimic materials or structures

    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
    主演
    0.43
     уто
    0.43
    았던
    0.42
    飲
    0.42
    醉
    0.42
    數量
    0.40
    記者
    0.39
    γκε
    0.39
    <0x80>
    0.38
    rological
    0.38
    POSITIVE LOGITS
     potenciales
    0.50
     átomos
    0.47
     biocompat
    0.47
     maca
    0.47
     constitucional
    0.45
     chromospheric
    0.45
     Lào
    0.45
    CreationFailed
    0.44
    ামিন
    0.44
     creazione
    0.44
    Activations Density 0.000%

    No Known Activations