© 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. 190
    Prev
    Next
    INDEX
    Explanations

    working towards goals

    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
     популярных
    1.27
     terken
    1.21
     nephews
    1.20
     irrég
    1.14
     깜
    1.14
    愕
    1.13
     أشهر
    1.12
    忍不住
    1.12
    跤
    1.12
    胞
    1.11
    POSITIVE LOGITS
     goals
    2.81
     objectives
    2.75
     goal
    2.72
     aims
    2.51
    goals
    2.48
    goal
    2.43
     Goals
    2.34
    Goals
    2.26
     aim
    2.26
     Objectives
    2.20
    Activations Density 1.167%

    No Known Activations