© 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. 2698
    Prev
    Next
    INDEX
    Explanations

    code blocks

    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
    uptools
    3.33
    т
    3.24
    ை
    3.17
    此之外
    3.17
    ੀ
    3.08
    sion
    3.08
    ו
    2.88
    sila
    2.88
    ぇ
    2.86
    sy
    2.82
    POSITIVE LOGITS
    ed
    3.23
    naires
    2.89
    naire
    2.68
    ized
    2.41
    ett
    2.30
    że
    2.29
    ସ୍
    2.28
     რ
    2.27
     rspace
    2.26
    ́p
    2.25
    Activations Density 1.374%

    No Known Activations