© 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. 188928
    Prev
    Next
    INDEX
    Explanations

    specifications and versions

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

    Product Vision

    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
    Парт
    0.54
    エル
    0.50
    Ｌ
    0.48
    楼主
    0.47
     sanguine
    0.47
    빛
    0.47
     maiores
    0.46
    Ｋ
    0.46
    ಿಸಿ
    0.45
     percol
    0.45
    POSITIVE LOGITS
     struktur
    0.50
    लीम
    0.46
     verbinden
    0.45
     Bridget
    0.44
    ност
    0.43
    stä
    0.43
    successful
    0.43
     früh
    0.42
    ণ্ডে
    0.42
     estructura
    0.41
    Activations Density 0.000%

    No Known Activations