© 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. 243904
    Prev
    Next
    INDEX
    Explanations

    names, places, and financial terms

    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
    fters
    0.41
    బె
    0.39
    檚
    0.38
     erhielt
    0.38
    동산
    0.38
    젯
    0.38
    女
    0.37
    KIS
    0.37
     hung
    0.37
     HUN
    0.37
    POSITIVE LOGITS
    ۵
    0.51
     জীবনের
    0.50
    ５
    0.50
    umo
    0.49
    ר
    0.48
     commen
    0.46
     Arduino
    0.45
    Logical
    0.45
     одному
    0.45
     summaries
    0.45
    Activations Density 0.001%

    No Known Activations