© 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. 13-GEMMASCOPE-2-RES-16K
    7. 5688
    Prev
    Next
    INDEX
    Explanations

    toxic chemicals

    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
    اوم
    1.34
    魎
    1.28
    いくつか
    1.25
    fuzzy
    1.23
    amiya
    1.23
    ayside
    1.21
    봤
    1.20
    鲽
    1.19
    zés
    1.18
    쏴
    1.17
    POSITIVE LOGITS
     bilgi
    1.36
    λευτα
    1.35
     égale
    1.31
     divid
    1.19
     info
    1.17
    WebContent
    1.16
     humanidad
    1.16
     inicio
    1.14
     mediante
    1.14
    力的
    1.13
    Activations Density 0.000%

    No Known Activations