© 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. 156020
    Prev
    Next
    INDEX
    Explanations

    "we" followed by verbs

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

    various actions and events

    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
    SCI
    0.50
     dovrà
    0.50
    лізу
    0.49
    斯
    0.49
     vettore
    0.48
     khoa
    0.47
    ǚ
    0.47
     urząd
    0.46
     momenti
    0.46
     społecz
    0.46
    POSITIVE LOGITS
    '
    0.62
    ips
    0.49
    ysis
    0.49
    rait
    0.48
    ats
    0.48
    isy
    0.48
    a
    0.47
    lal
    0.46
    itaria
    0.46
    aya
    0.44
    Activations Density 0.000%

    No Known Activations