© 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. 21332
    Prev
    Next
    INDEX
    Explanations

    product description

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

    product information

    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
    ^{*}=\
    0.50
    マーケ
    0.48
    माइंडर
    0.48
    épend
    0.46
    attaque
    0.45
     Ethn
    0.45
    ifers
    0.44
    atge
    0.44
    ग्राम
    0.44
    igay
    0.44
    POSITIVE LOGITS
     холо
    0.50
     냉
    0.46
     볼
    0.45
     muffler
    0.45
     중요한
    0.43
    Regulation
    0.42
     जिसने
    0.42
     wichtigsten
    0.41
     weiteren
    0.41
     고
    0.40
    Activations Density 0.000%

    No Known Activations