© 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. 9468
    Prev
    Next
    INDEX
    Explanations

    words ending in -ed, -y, or -er

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

    descriptive words and states

    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
     ደረጃ
    0.47
     понимают
    0.46
     স্পষ্ট
    0.46
     Ҳ
    0.45
    ស្ថានភាព
    0.44
     Україні
    0.44
     トート
    0.42
     ক্যান্সার
    0.42
     mieście
    0.42
    టింగ్
    0.41
    POSITIVE LOGITS
    ل
    0.74
    s
    0.73
    A
    0.64
    E
    0.64
    G
    0.63
    ات
    0.62
    the
    0.60
    d
    0.60
    l
    0.59
    ه
    0.59
    Activations Density 0.222%

    No Known Activations