© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 16-GEMMASCOPE-2-RES-16K
    7. 15160
    Prev
    Next
    INDEX
    Explanations

    time before or after

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

    time duration periods seasons

    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_16_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
    h
    1.50
     as
    1.09
    r
    1.09
    CT
    1.01
    OS
    1.01
    IA
    1.01
    OP
    0.95
    CC
    0.95
    OD
    0.95
    ně
    0.94
    POSITIVE LOGITS
    ן
    1.19
    ל
    1.16
    ’
    1.09
     an
    1.08
    </h2>
    0.97
    :
    0.96
    ives
    0.94
    اک
    0.94
    ם
    0.93
    )
    0.93
    Activations Density 0.288%

    No Known Activations