© 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-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 170
    Prev
    Next
    INDEX
    Explanations

    may be, can be, offer discounts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cenário
    1.08
    Ữ
    1.04
     estrateg
    1.03
     böyle
    1.03
     negócios
    1.01
    burgo
    1.00
    ហារ
    1.00
    lina
    1.00
    hrlich
    0.98
    ೋಜನ
    0.98
    POSITIVE LOGITS
     alphabetically
    0.94
     piece
    0.92
    вет
    0.91
     ακόμα
    0.90
    под
    0.88
     else
    0.87
    자
    0.87
     manually
    0.87
     들어가
    0.87
    명을
    0.85
    Activations Density 0.000%

    No Known Activations