© 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. 37643
    Prev
    Next
    INDEX
    Explanations

    phrasal verbs and common actions

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

    text and images inputs

    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
     ২০২২
    0.98
     проєкту
    0.95
    令和
    0.94
    🫶
    0.91
     ২০২৩
    0.91
     проє
    0.89
    https
    0.88
    TikTok
    0.86
     २०२
    0.83
     reimag
    0.83
    POSITIVE LOGITS
     equipments
    0.64
     iPod
    0.60
     AOL
    0.58
     Orissa
    0.55
     http
    0.54
    http
    0.52
     চিকিত
    0.52
     Informations
    0.51
    ゎ
    0.51
     ২০১০
    0.51
    Activations Density 0.018%

    No Known Activations