© 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. 98529
    Prev
    Next
    INDEX
    Explanations

    ball mill, WIN, hammer, United States

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

    downscale, game terminology, administrative processing, flight home

    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
     தேவை
    0.44
    ा
    0.44
    operasi
    0.43
    increases
    0.42
     مبنی
    0.42
    robo
    0.42
     Aplic
    0.41
    asını
    0.41
     హైదర్
    0.40
     Blog
    0.40
    POSITIVE LOGITS
     acontecer
    0.55
    依旧
    0.54
     callbacks
    0.52
     চলচ্চিত্র
    0.50
    🫶
    0.49
     vibes
    0.48
     đậm
    0.47
    ไตล์
    0.46
     gastronomy
    0.46
     vibe
    0.45
    Activations Density 0.003%

    No Known Activations