© 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. 13409
    Prev
    Next
    INDEX
    Explanations

    understanding without agreement

    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
    räume
    2.43
    richter
    2.35
    榈
    2.24
    வே
    2.22
    b
    2.22
    ਗੀ
    2.20
     lẽ
    2.20
     εκεί
    2.19
    srand
    2.16
    r
    2.12
    POSITIVE LOGITS
    izumab
    3.23
    سى
    2.85
    ྦ
    2.70
    она
    2.70
     Continuum
    2.62
    ྨ
    2.61
    蒡
    2.61
    oglycos
    2.57
    ⇅
    2.55
     regulatory
    2.53
    Activations Density 0.010%

    No Known Activations