© 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. 218861
    Prev
    Next
    INDEX
    Explanations

    federal tax, ensure your

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

    referencing context or subsequent details

    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
    ta
    0.50
     serem
    0.45
     gấp
    0.45
    pi
    0.44
    r
    0.44
     panjang
    0.43
    üyük
    0.43
     hearts
    0.41
     عزی
    0.41
    ما
    0.41
    POSITIVE LOGITS
     voisinage
    0.49
    ர்ஸ்
    0.48
    ଣ
    0.48
     চুম্বন
    0.46
    ᑉ
    0.46
    etí
    0.45
     subsp
    0.45
     lors
    0.45
    ුණු
    0.45
    iunea
    0.44
    Activations Density 0.001%

    No Known Activations