© 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. 222678
    Prev
    Next
    INDEX
    Explanations

    hanging planters

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

    words from many languages

    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
    же
    0.52
    quen
    0.50
    при
    0.49
    форми
    0.49
    хо
    0.48
    ö
    0.48
    पृथ
    0.47
    طاء
    0.46
    還有
    0.46
    開封
    0.46
    POSITIVE LOGITS
     niềm
    0.52
     حصے
    0.47
     महीनों
    0.47
     ressembl
    0.46
     شی
    0.46
     đỉnh
    0.45
     грошы
    0.45
    omini
    0.45
    \{\
    0.44
     دی
    0.44
    Activations Density 0.001%

    No Known Activations