© 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
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 9487
    Prev
    Next
    INDEX
    Explanations

    numbers followed by closing punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_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
     Funeral
    1.05
    Funeral
    1.04
     K
    0.92
     жизни
    0.88
     Fred
    0.87
     Temple
    0.87
     mariage
    0.86
     condolences
    0.86
     two
    0.85
     yet
    0.85
    POSITIVE LOGITS
     کہتے
    1.03
     உள்ளன
    1.02
    áticas
    1.02
    ması
    1.01
     pokazuje
    1.00
    㔯
    1.00
    muş
    1.00
    owały
    0.99
     fornisce
    0.99
     tecnológico
    0.97
    Activations Density 0.004%

    No Known Activations