© 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. 3607
    Prev
    Next
    INDEX
    Explanations

    just outside the top

    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
    sman
    3.06
    s
    2.52
    eh
    2.52
    اخ
    2.38
    sam
    2.35
    e
    2.31
    es
    2.31
    า
    2.27
    shed
    2.26
    ا
    2.23
    POSITIVE LOGITS
     thisComponent
    2.23
     dialing
    2.16
    ‖</
    2.14
     pept
    2.07
    𝚘
    2.04
    𝚒
    2.04
     somewhat
    2.03
     compuls
    2.01
    𝐩
    2.00
     stocking
    1.99
    Activations Density 0.000%

    No Known Activations