© 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. 1918
    Prev
    Next
    INDEX
    Explanations

    multilingual content and specific cases

    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
    ypress
    1.26
    tern
    1.21
     arrow
    1.21
     geometry
    1.20
     beacon
    1.19
    velope
    1.19
     Geometry
    1.18
    н
    1.18
    cery
    1.16
     valentine
    1.15
    POSITIVE LOGITS
    ੁਰ
    1.40
    坻
    1.34
    解读
    1.30
     réc
    1.26
    となった
    1.24
    土
    1.23
    IsIn
    1.22
    皱
    1.22
    ものの
    1.21
    逾
    1.21
    Activations Density 0.000%

    No Known Activations