© 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. 138027
    Prev
    Next
    INDEX
    Explanations

    specific items and concepts

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

    phrases starting with specific 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
    বিজ্ঞ
    0.51
    मपुर
    0.50
    cadherin
    0.47
    notch
    0.45
     અમને
    0.44
    休
    0.43
     গাজী
    0.42
    tiered
    0.42
    马
    0.42
    lığı
    0.41
    POSITIVE LOGITS
    Themes
    0.53
    »;
    0.51
     распоря
    0.47
     »,
    0.47
    »,
    0.47
     diverses
    0.46
     некоторое
    0.45
     beant
    0.44
    »،
    0.44
     \*
    0.44
    Activations Density 0.001%

    No Known Activations