© 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. 547
    Prev
    Next
    INDEX
    Explanations

    activity/learning tasks

    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
     unquestionably
    1.46
     inasmuch
    1.22
     undeniably
    1.21
     insofar
    1.19
     весьма
    1.17
     criminally
    1.15
     relativement
    1.15
    ̿
    1.15
     dissident
    1.15
     undoubtedly
    1.13
    POSITIVE LOGITS
     worksheet
    1.87
    练习
    1.79
     brainstorm
    1.77
     brainstorming
    1.67
     learners
    1.65
     quizzes
    1.64
     quiz
    1.63
     classroom
    1.54
     sensory
    1.54
     worksheets
    1.54
    Activations Density 1.539%

    No Known Activations