© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 6633
    Prev
    Next
    INDEX
    Explanations

    focus on attention

    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
    চ্চার
    2.73
    م
    2.71
    til
    2.60
    észet
    2.58
    stration
    2.58
    icarboxylic
    2.57
    ted
    2.51
    трим
    2.49
    rd
    2.48
     المللی
    2.47
    POSITIVE LOGITS
    ي
    2.74
    ます
    2.63
    стина
    2.52
    ุล
    2.50
    in
    2.42
    ือ
    2.41
    ী
    2.36
    𝒊
    2.33
    enters
    2.31
    inata
    2.31
    Activations Density 0.352%

    No Known Activations