© 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. 183530
    Prev
    Next
    INDEX
    Explanations

    market outlook

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

    phrases before punctuation

    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
     Jahn
    0.49
     providers
    0.46
    alles
    0.45
     ava
    0.45
     %),
    0.44
     Geb
    0.44
     Ses
    0.43
     Dearborn
    0.43
    त्मक
    0.43
     Receive
    0.43
    POSITIVE LOGITS
    𝒐
    0.50
    ഓം
    0.48
    飾り
    0.47
    思い出
    0.46
    MAJOR
    0.45
    кульп
    0.45
    tempCard
    0.45
    取り付け
    0.45
     integração
    0.45
    送
    0.44
    Activations Density 0.000%

    No Known Activations