© 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. 58839
    Prev
    Next
    INDEX
    Explanations

    available which, domains names

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

    Instagram future Stories Income Better communication

    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
    ⅰ
    0.48
    Ⅱ
    0.47
     सुधार
    0.46
    葡
    0.46
    unjukkan
    0.45
    ği
    0.44
    展现
    0.43
    Ⅰ
    0.43
    เด
    0.43
     ngọt
    0.43
    POSITIVE LOGITS
     Balm
    0.51
     karm
    0.48
     Ashram
    0.46
     Donnelly
    0.46
     inici
    0.46
    نيا
    0.46
     Avalon
    0.46
     Karma
    0.45
     toll
    0.45
     Following
    0.44
    Activations Density 0.000%

    No Known Activations