© 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. 73209
    Prev
    Next
    INDEX
    Explanations

    rising damp

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

    complex punctuation and structure

    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
    ندوق
    0.54
    اندان
    0.54
    ط
    0.51
    liver
    0.50
    igis
    0.49
    ث
    0.48
    мпа
    0.46
    ز
    0.46
    azolin
    0.45
    alchemy
    0.45
    POSITIVE LOGITS
     Featured
    0.51
     段
    0.50
     যুক্ত
    0.48
     Elytres
    0.48
     ধ্বংস
    0.47
     కార్
    0.46
     ‚
    0.46
     собі
    0.46
     Ashraf
    0.46
     зру
    0.46
    Activations Density 0.002%

    No Known Activations