© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 2194
    Prev
    Next
    INDEX
    Explanations

    blurring lines between

    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_65k_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
    ₂,
    1.19
    、“
    1.13
     ،
    1.11
    ríklad
    1.11
    __,
    1.10
    các
    1.09
    ,
    1.08
    éseket
    1.07
    たとえば
    1.06
    ،
    1.06
    POSITIVE LOGITS
     lovely
    1.24
     vinegar
    1.12
     nice
    1.12
     tasteful
    1.11
     可愛
    1.10
     皆
    1.09
     haha
    1.09
     ;)
    1.08
     stupidity
    1.08
     yummy
    1.05
    Activations Density 0.482%

    No Known Activations