© 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. 137703
    Prev
    Next
    INDEX
    Explanations

    taxi fares and sales

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

    limitation of, necessarily, signature

    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
     niektó
    0.48
     quibusdam
    0.47
     overwrite
    0.46
     spermato
    0.46
    髋
    0.46
     Vật
    0.45
     Сурикова
    0.45
     Gerais
    0.44
     alguns
    0.44
    𝘻
    0.44
    POSITIVE LOGITS
    f
    0.53
    했지만
    0.51
     বাড়ছে
    0.51
     Thursday
    0.49
    Thursday
    0.48
    prices
    0.47
    x
    0.45
     Friday
    0.45
    post
    0.44
    rose
    0.44
    Activations Density 0.000%

    No Known Activations