© 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
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 4391
    Prev
    Next
    INDEX
    Explanations

    animals and predators

    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
    𝚘
    2.40
    𝚢
    2.22
    𝚊
    2.06
     trifle
    2.06
     carpentry
    2.05
    𝚕
    2.01
    iesz
    2.00
    ueda
    1.99
    ertown
    1.98
     silence
    1.97
    POSITIVE LOGITS
    asar
    2.17
    ط
    2.16
    竺
    2.13
    ยนต์
    2.11
     MAKEINTRESOURCE
    2.10
    ي
    2.10
    مش
    2.07
    ب
    2.05
    ৃত্তি
    2.03
    τία
    1.92
    Activations Density 1.020%

    No Known Activations