© 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. 115144
    Prev
    Next
    INDEX
    Explanations

    we acquired / makes us / going to

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

    financial and numerical concepts

    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
    通讯
    0.53
     empê
    0.51
     może
    0.47
     Hosp
    0.46
    扬
    0.45
     proteins
    0.43
     şey
    0.43
    工作人员
    0.42
    的服务
    0.42
     gloves
    0.42
    POSITIVE LOGITS
    defined
    0.52
    placeholder
    0.47
    our
    0.47
    las
    0.47
    sinx
    0.47
     qued
    0.46
    myLabels
    0.45
    結
    0.45
    rewrite
    0.45
     redeemed
    0.44
    Activations Density 0.001%

    No Known Activations