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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 112
    Prev
    Next
    INDEX
    Explanations

    Mavic, L-Shape, B

    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
    y
    2.13
    u
    1.81
    a
    1.74
    i
    1.71
    e
    1.69
    る
    1.63
    in
    1.52
    o
    1.51
    er
    1.51
    י
    1.45
    POSITIVE LOGITS
    𝚎
    1.37
    
    1.28
    ünü
    1.27
    ünün
    1.25
    inii
    1.24
    Г
    1.24
    қы
    1.22
    𝐧
    1.21
    Ла
    1.20
    Além
    1.20
    Activations Density 0.947%

    No Known Activations