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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 2634
    Prev
    Next
    INDEX
    Explanations

    a with punctuation or numbers

    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
    erful
    2.21
    ምት
    2.15
    পোষ
    2.12
    糸
    2.05
    acchati
    2.04
    ف
    1.98
    عال
    1.93
    uptools
    1.92
    جھ
    1.90
     Phaser
    1.87
    POSITIVE LOGITS
    рифмети
    2.24
    raham
    2.23
    angement
    2.19
    robat
    2.02
    壳
    2.01
    ትክል
    2.00
     Crystallogr
    1.98
    AE
    1.97
    ypter
    1.96
    STRACT
    1.90
    Activations Density 1.802%

    No Known Activations