© 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. 224231
    Prev
    Next
    INDEX
    Explanations

    prepositions and conjunctions

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

    NPCs and non-English characters

    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
     اکتوبر
    0.52
    شنبه
    0.43
     قیمت
    0.42
    വരുടെ
    0.41
     הראש
    0.41
     ات
    0.40
     °,
    0.40
     UNICEF
    0.40
     criminality
    0.40
     температуре
    0.40
    POSITIVE LOGITS
    ixin
    0.49
    фи
    0.47
    ü
    0.45
    腰
    0.45
    켐
    0.45
    ilibr
    0.43
    uu
    0.43
    Salve
    0.43
    iiii
    0.43
    裱
    0.43
    Activations Density 0.000%

    No Known Activations