© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 14004
    Prev
    Next
    INDEX
    Explanations

    light roast levels

    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
    ുട
    2.48
    produto
    2.20
    <bos>
    2.19
    Voor
    2.18
    rebbe
    2.15
    ेड
    2.08
    Internal
    2.06
    radiol
    2.05
    शुदा
    2.05
    ugd
    2.05
    POSITIVE LOGITS
    कुंठ
    2.45
    itorial
    2.28
    anine
    2.11
    ા
    2.08
    
    2.04
     kese
    2.04
    𝑎
    2.03
    ⃛
    2.00
    anav
    1.99
     바탕
    1.97
    Activations Density 0.024%

    No Known Activations