© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1642
    Prev
    Next
    INDEX
    Explanations

    time indicatorsday, today, tomorrow, tonight

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
    ာ
    1.71
     năm
    1.53
    getIndex
    1.52
    மிழ்
    1.49
    ERV
    1.48
    tei
    1.44
    ɸ
    1.42
     st
    1.41
     імені
    1.40
    erte
    1.38
    POSITIVE LOGITS
     afternoon
    2.07
     viernes
    2.03
     soir
    1.95
    ചര്യ
    1.94
     jueves
    1.92
     miércoles
    1.90
     Sabtu
    1.89
     mercredi
    1.88
     morning
    1.88
     martes
    1.86
    Activations Density 0.694%

    No Known Activations