© 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. 16151
    Prev
    Next
    INDEX
    Explanations

    1

    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
    ajemen
    1.26
    ภู
    1.17
    <0xAB>
    1.09
    ϑ
    1.08
    IW
    1.07
    Ig
    1.06
    Нау
    1.06
    築
    1.04
    勬
    1.03
     antitumor
    1.02
    POSITIVE LOGITS
     каждое
    1.74
     every
    1.63
     каждый
    1.61
     Every
    1.59
     jeder
    1.55
     каждую
    1.42
     प्रत्येक
    1.38
     Each
    1.37
     setiap
    1.37
     każde
    1.36
    Activations Density 0.198%

    No Known Activations