© 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. 2496
    Prev
    Next
    INDEX
    Explanations

    Alex, incredibly large, patterns

    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
    かで
    1.19
     તેને
    1.09
     kaldı
    1.08
    ⟋
    1.04
     維尼
    1.04
    푠
    1.03
     tore
    1.03
    .¹
    1.02
    '،
    1.02
    Ûn
    1.01
    POSITIVE LOGITS
    innis
    1.02
    Aud
    0.99
    Is
    0.96
    зів
    0.94
    Dy
    0.91
    Bis
    0.91
    Lum
    0.89
    न्‍
    0.89
    Pres
    0.88
    aud
    0.88
    Activations Density 16.890%

    No Known Activations