© 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. 189654
    Prev
    Next
    INDEX
    Explanations

    names on the list

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

    monomers, app, influence, and SEO

    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
    ها
    0.47
    т
    0.46
    ях
    0.46
    ек
    0.46
    г
    0.45
    ме
    0.45
    НЯ
    0.45
    ма
    0.45
    λα
    0.44
    вана
    0.44
    POSITIVE LOGITS
     indigestion
    0.55
     înd
    0.47
     विटामिन
    0.47
    ційних
    0.47
     সন্
    0.46
     }^{*}$
    0.46
    用の
    0.46
     convirt
    0.45
     डिग्री
    0.45
    𝘄
    0.45
    Activations Density 0.000%

    No Known Activations