© 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. 114354
    Prev
    Next
    INDEX
    Explanations

    category management, youth services, following is

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

    delivery?

    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
     Luzon
    0.55
     b
    0.53
     metam
    0.53
     Luffy
    0.52
     fence
    0.50
     phag
    0.50
     remuneration
    0.49
     perfor
    0.48
     haies
    0.47
     Wifi
    0.46
    POSITIVE LOGITS
    ຜະລິດຕະພັນ
    0.55
    EC
    0.54
    文艺
    0.51
     höheren
    0.50
    ТУ
    0.49
    ಅ
    0.49
    Wein
    0.48
    코
    0.48
    ライン
    0.48
    ز
    0.48
    Activations Density 0.000%

    No Known Activations