© 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. 139543
    Prev
    Next
    INDEX
    Explanations

    year ahead

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

    year followed by a specific year

    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
    ك
    0.79
     ENEM
    0.76
     poeta
    0.76
     compañero
    0.73
     نویس
    0.71
     allons
    0.70
     antico
    0.70
    ल
    0.70
     órgano
    0.69
     இயக்குனர்
    0.69
    POSITIVE LOGITS
    Year
    0.97
    EL
    0.97
    ML
    0.95
    AR
    0.93
    YEAR
    0.92
    AN
    0.89
    AV
    0.87
    AD
    0.86
    IN
    0.85
    IT
    0.85
    Activations Density 0.253%

    No Known Activations