© 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. 80739
    Prev
    Next
    INDEX
    Explanations

    noun followed by preposition

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

    Box 12 codes, biographies

    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
    uš
    0.56
     взаимодей
    0.55
     ชอบ
    0.54
     می
    0.52
     ロゴ
    0.52
     oczy
    0.52
     マーク
    0.52
    𝗴
    0.52
     logró
    0.51
     należy
    0.50
    POSITIVE LOGITS
     sleepers
    0.50
     RSI
    0.49
     installations
    0.46
     Culinary
    0.46
     traditional
    0.45
     Obsidian
    0.44
     Tumblr
    0.44
     Singers
    0.44
    ,
    0.43
     RS
    0.43
    Activations Density 0.000%

    No Known Activations