© 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. 44453
    Prev
    Next
    INDEX
    Explanations

    multi-lingual description or context

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

    offering or seeking advice

    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
    &
    0.49
     homme
    0.46
     leased
    0.46
     entrepreneurial
    0.46
     Land
    0.44
     capitalists
    0.44
     본
    0.44
     freehold
    0.44
     phosphorylated
    0.42
     oceans
    0.42
    POSITIVE LOGITS
    同事
    0.48
    AL
    0.46
    เหมือน
    0.45
    🖌
    0.45
     colegas
    0.45
     escenario
    0.44
     maquillaje
    0.44
     drauf
    0.43
    队友
    0.43
     nemus
    0.43
    Activations Density 0.000%

    No Known Activations