© 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. 1634
    Prev
    Next
    INDEX
    Explanations

    h followed by punctuation or word start

    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
    hene
    2.60
     agree
    2.40
    hese
    2.37
     root
    2.30
    rige
    2.28
    radle
    2.28
    r
    2.27
    bies
    2.26
    ധി
    2.24
    hanging
    2.21
    POSITIVE LOGITS
    izontal
    3.78
    ክምና
    3.60
    蟆
    3.33
    ằng
    3.28
     indexRouter
    3.26
    hhh
    3.23
    ഒരു
    3.19
    疸
    3.16
     teil
    3.11
    Ꮳ
    3.10
    Activations Density 1.509%

    No Known Activations