© 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. 34046
    Prev
    Next
    INDEX
    Explanations

    quantities and time periods

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

    for now

    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
    m
    0.53
    t
    0.51
     আইনজীবী
    0.46
     Management
    0.46
     Administration
    0.45
     Tem
    0.44
    et
    0.44
    upp
    0.41
     với
    0.41
    ].
    0.40
    POSITIVE LOGITS
    जीलैंड
    0.49
     годы
    0.46
    ्रेंस
    0.45
     крупных
    0.45
     decades
    0.43
     ஆண்டுகள்
    0.43
     years
    0.41
    FilesIn
    0.41
     иных
    0.41
     отдельных
    0.40
    Activations Density 0.000%

    No Known Activations