© 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. 137597
    Prev
    Next
    INDEX
    Explanations

    months and dates

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

    months or titles

    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
    亚
    0.54
    ادیه
    0.54
    yahoo
    0.54
    ᵐ
    0.52
    โทร
    0.52
    τσ
    0.51
    邓
    0.51
    ką
    0.50
    碾
    0.50
    arranty
    0.49
    POSITIVE LOGITS
     December
    0.54
     reaches
    0.52
    0.50
     reached
    0.49
     October
    0.48
     November
    0.48
     President
    0.47
     February
    0.47
     Shakespeare
    0.47
     King
    0.47
    Activations Density 0.000%

    No Known Activations