© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3569
    Prev
    Next
    INDEX
    Explanations

    arguably the most

    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
    ▟
    1.73
    GetBytes
    1.69
     Perché
    1.64
    糬
    1.63
    𝑖
    1.62
    🫦
    1.62
    𝑔
    1.61
     Đế
    1.60
    🧿
    1.60
    iliter
    1.60
    POSITIVE LOGITS
    ur
    1.28
    ov
    1.26
    prochen
    1.22
    ak
    1.21
    c
    1.16
    j
    1.15
        
    1.14
     staff
    1.12
     lent
    1.12
    ever
    1.11
    Activations Density 0.388%

    No Known Activations