© 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. 13526
    Prev
    Next
    INDEX
    Explanations

    args)

    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
     undertaking
    1.61
    s
    1.53
     ​​
    1.46
    bhp
    1.40
     learning
    1.33
     also
    1.31
    oos
    1.28
     copies
    1.25
    t
    1.25
     undertook
    1.24
    POSITIVE LOGITS
     সমূহ
    1.90
     Jefe
    1.86
    чина
    1.83
    kaç
    1.83
     faltando
    1.76
     Durchschnitt
    1.76
    ttore
    1.76
     tř
    1.72
    閭
    1.69
     grabado
    1.68
    Activations Density 0.016%

    No Known Activations