© 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. 7-GEMMASCOPE-2-RES-16K
    7. 14279
    Prev
    Next
    INDEX
    Explanations

    under

    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_7_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
    yiz
    2.88
    т
    2.75
    ج
    2.73
    t
    2.71
    in
    2.69
    sle
    2.65
    itze
    2.61
    沸
    2.51
    s
    2.49
     Kxg
    2.47
    POSITIVE LOGITS
    ल्याण
    2.82
    𝐬
    2.80
    ੌਰ
    2.80
    𝐥
    2.69
    foils
    2.48
    橥
    2.48
    ژی
    2.46
    ैसे
    2.46
    ican
    2.44
    𝐚
    2.42
    Activations Density 0.018%

    No Known Activations