© 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. 218412
    Prev
    Next
    INDEX
    Explanations

    Association announced

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

    previous concepts or clauses

    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
    гин
    0.48
     быст
    0.48
     എസ്
    0.48
     ї
    0.48
     กับ
    0.48
     軽量
    0.46
     やつ
    0.46
    ûr
    0.46
     इस्तेमाल
    0.45
     terdiri
    0.44
    POSITIVE LOGITS
    ع
    0.60
    ين
    0.56
    isierte
    0.46
    Profession
    0.46
    「
    0.46
    سا
    0.46
     areas
    0.45
    Dropdown
    0.45
    Marg
    0.45
    逐
    0.44
    Activations Density 0.000%

    No Known Activations