© 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. 206387
    Prev
    Next
    INDEX
    Explanations

    languages and technical terms

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

    like it or like you

    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
     hiểu
    0.51
    rared
    0.46
    也能
    0.44
     ফলে
    0.43
     স্বীকার
    0.43
    ิด
    0.43
     نتیجه
    0.42
     !==
    0.42
    INET
    0.42
     材質
    0.42
    POSITIVE LOGITS
     provas
    0.46
     Ци
    0.46
    Ци
    0.46
     ausgew
    0.43
     escolh
    0.42
    Произ
    0.41
    Цена
    0.41
     selecion
    0.41
     Equations
    0.40
     damning
    0.40
    Activations Density 0.000%

    No Known Activations