© 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. 795
    Prev
    Next
    INDEX
    Explanations

    The [Topic]

    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
     ?.
    1.32
     ().
    1.31
     مِن
    1.29
    .​
    1.29
     consecutively
    1.27
    ِ
    1.25
    ۔
    1.25
    .‏
    1.24
     variously
    1.23
     successively
    1.23
    POSITIVE LOGITS
     문제는
    2.00
     υπάρχει
    1.83
     insanlar
    1.81
    이는
    1.77
     tarefa
    1.74
     μπορεί
    1.74
     사람은
    1.72
     pessoas
    1.70
     equipes
    1.69
     δεν
    1.69
    Activations Density 1.265%

    No Known Activations