© 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. 59504
    Prev
    Next
    INDEX
    Explanations

    possessive endings, conjunctions, prepositions, and foreign words

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

    words followed by specific details

    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
    라이
    0.50
    žila
    0.49
    ഹാ
    0.47
    ના
    0.46
     bustling
    0.46
    মনি
    0.45
    claimer
    0.45
    좀
    0.45
    ⓤ
    0.44
    CQL
    0.43
    POSITIVE LOGITS
     neoplastic
    0.56
     rheumatoid
    0.49
    oseconds
    0.49
     ਕੋ
    0.45
     myosin
    0.44
     एलर्जी
    0.44
    丕
    0.44
     rheumat
    0.44
     البح
    0.43
    embry
    0.43
    Activations Density 0.000%

    No Known Activations