© 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. 18266
    Prev
    Next
    INDEX
    Explanations

    professional business

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

    text to number

    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
     horno
    0.44
     (!
    0.41
    ！（
    0.41
    （
    0.39
     (
    0.38
     живота
    0.37
     সমাধি
    0.36
     (!)
    0.36
    acho
    0.35
    cumulative
    0.35
    POSITIVE LOGITS
     protože
    0.50
     fordi
    0.48
    当局
    0.47
     deoarece
    0.47
     alın
    0.47
     omdat
    0.45
    కరణ
    0.45
     koska
    0.44
    է
    0.43
    尴
    0.42
    Activations Density 0.000%

    No Known Activations