© 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. 14606
    Prev
    Next
    INDEX
    Explanations

    hedged, hedonic, hedging

    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
    s
    2.92
    ে
    2.75
    денти
    2.75
    ের
    2.74
    ﺙ
    2.50
    <h6>
    2.42
    ધાર
    2.42
    丿
    2.41
     государства
    2.37
     ``
    2.37
    POSITIVE LOGITS
    InSection
    2.72
    ಿನ
    2.59
    eket
    2.45
    eventId
    2.43
    mohan
    2.40
     brz
    2.39
    workItem
    2.38
    ek
    2.36
    Ans
    2.32
    onyms
    2.31
    Activations Density 0.004%

    No Known Activations