© 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. 190740
    Prev
    Next
    INDEX
    Explanations

    information is incorrect

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

    inclusive

    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
    濤
    0.52
     buddhist
    0.51
     बनकर
    0.51
    QUA
    0.51
     ہوئی
    0.50
     प्रोफेसर
    0.50
    戀
    0.50
     τό
    0.50
    為主
    0.50
    過了
    0.50
    POSITIVE LOGITS
    badbreak
    0.45
     rearrangements
    0.44
    illeurs
    0.43
    whats
    0.43
    ish
    0.43
    nah
    0.43
     конструк
    0.42
     enhancements
    0.42
    rd
    0.42
     শক্ত
    0.42
    Activations Density 0.000%

    No Known Activations