© 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. 190772
    Prev
    Next
    INDEX
    Explanations

    annual events and dates

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

    critical and data updates

    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
    r
    0.51
    ني
    0.51
    s
    0.47
    pumpkin
    0.46
    ni
    0.45
    スマホ
    0.44
    nte
    0.43
    isah
    0.43
    挕
    0.42
    🧅
    0.42
    POSITIVE LOGITS
     annually
    0.54
     dates
    0.50
     annuel
    0.50
     commemorating
    0.49
     fechas
    0.49
     "...
    0.48
     annuelle
    0.48
    每年
    0.47
     명
    0.46
     nominees
    0.46
    Activations Density 0.000%

    No Known Activations