© 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. 224925
    Prev
    Next
    INDEX
    Explanations

    Bosch products and divisions

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

    offer input

    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
     bárm
    0.55
     Pensacola
    0.44
     incarcerated
    0.43
    Whenever
    0.43
    ق
    0.43
     pels
    0.43
     investigated
    0.42
     inundated
    0.42
    Otros
    0.42
     fabricated
    0.41
    POSITIVE LOGITS
     하며
    0.49
    ？
    0.47
     כמו
    0.46
     مانند
    0.45
    ？）
    0.45
     อาท
    0.44
     الزمن
    0.44
    みたいな
    0.42
     như
    0.42
     médiocrement
    0.41
    Activations Density 0.000%

    No Known Activations