© 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. 153574
    Prev
    Next
    INDEX
    Explanations

    words like guys live

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

    Answers to questions

    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
     preservatives
    0.54
     medie
    0.51
     autent
    0.51
     vidéos
    0.48
    病例
    0.47
     perdu
    0.47
     nf
    0.47
    a
    0.47
     veterin
    0.46
    conten
    0.46
    POSITIVE LOGITS
     format
    0.44
    )}$
    0.42
     دې
    0.42
    לך
    0.41
    كى
    0.41
     ס
    0.40
    스
    0.40
    ক্ষ
    0.40
     그
    0.39
     dictionary
    0.39
    Activations Density 0.000%

    No Known Activations