© 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. 13568
    Prev
    Next
    INDEX
    Explanations

    magnética, aprendizaje, negocio, Moscú, rotor, net

    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
    ܦ
    1.70
     definitiv
    1.64
     drake
    1.64
     sekar
    1.60
     flam
    1.59
     hitter
    1.59
     الَّ
    1.58
    rase
    1.55
    𒌑
    1.54
     chwil
    1.52
    POSITIVE LOGITS
     nationalities
    1.31
    Registered
    1.29
    ums
    1.20
    Benefits
    1.19
    ंध
    1.16
    umi
    1.15
     fulfil
    1.14
    Moreover
    1.14
    meed
    1.14
    меры
    1.13
    Activations Density 0.001%

    No Known Activations