© 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. 14987
    Prev
    Next
    INDEX
    Explanations

    log / or not limited

    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
     Somewhat
    1.56
    __/
    1.53
    得上
    1.51
    হ্ন
    1.47
     somewhat
    1.47
     acuerdo
    1.46
    Standards
    1.46
    vis
    1.45
    separable
    1.43
    ্তিক
    1.42
    POSITIVE LOGITS
    榔
    1.78
    agog
    1.71
    erce
    1.64
     Blüten
    1.63
     мон
    1.62
     Geb
    1.60
    orium
    1.59
    e
    1.58
    erar
    1.58
    eae
    1.58
    Activations Density 0.060%

    No Known Activations