© 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-16K
    7. 12188
    Prev
    Next
    INDEX
    Explanations

    year context

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

    year or years

    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_16k_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
    ल
    0.77
    abhavena
    0.76
    i
    0.74
     نویس
    0.70
     poeta
    0.70
    ಿ
    0.68
    ië
    0.68
    л
    0.68
     kamu
    0.66
    этому
    0.65
    POSITIVE LOGITS
    Year
    1.15
    YEAR
    1.09
    EL
    0.96
     year
    0.95
     Jahr
    0.94
     Year
    0.92
    AR
    0.91
    AT
    0.87
    ML
    0.85
    AL
    0.84
    Activations Density 0.367%

    No Known Activations