© 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. 34136
    Prev
    Next
    INDEX
    Explanations

    time periods

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

    Rising costs and resources

    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
    ated
    0.63
    rash
    0.51
    a
    0.50
    rie
    0.48
    sthe
    0.48
    nah
    0.48
    page
    0.48
    nine
    0.48
    path
    0.47
    stown
    0.47
    POSITIVE LOGITS
    Ꮸ
    0.52
    Doors
    0.48
    Ⅼ
    0.47
     Дж
    0.47
     ఏర్ప
    0.47
    Investors
    0.47
     일부
    0.46
    Recorded
    0.46
     দুর্ভিক্ষের
    0.46
     областях
    0.45
    Activations Density 0.004%

    No Known Activations