© 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. 7-GEMMASCOPE-2-RES-16K
    7. 14813
    Prev
    Next
    INDEX
    Explanations

    programming languages

    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_7_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
     many
    1.43
     Many
    1.41
     an
    1.37
     de
    1.35
     project
    1.29
     a
    1.29
     ambition
    1.28
     future
    1.28
     Un
    1.28
     event
    1.24
    POSITIVE LOGITS
    сен
    2.16
    ángulo
    1.94
    틸
    1.80
    писи
    1.74
    ណ្ត
    1.73
    Ⲑ
    1.70
    З
    1.67
    chyné
    1.67
    ..--..--
    1.66
    艹
    1.66
    Activations Density 0.030%

    No Known Activations