© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 14953
    Prev
    Next
    INDEX
    Explanations

    for loops

    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
    ة
    2.26
    at
    1.76
    ス
    1.74
    ル
    1.74
    us
    1.68
    л
    1.62
    на
    1.58
    ️
    1.56
    什么
    1.54
    a
    1.53
    POSITIVE LOGITS
    cht
    1.67
    রুখ
    1.57
    녕하십니까
    1.54
    जेस्टिव
    1.50
     foaf
    1.48
    ECTION
    1.47
    πων
    1.44
    novo
    1.42
     httpClient
    1.42
     textArea
    1.40
    Activations Density 0.030%

    No Known Activations