© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12039
    Prev
    Next
    INDEX
    Explanations

    prior to 1994

    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
    gap
    2.26
     aho
    2.23
    oyam
    2.23
    agra
    2.22
    antiti
    2.12
    ritu
    2.08
    𝐓
    2.05
    ómo
    2.04
    wiad
    2.04
    mvnrepository
    2.03
    POSITIVE LOGITS
    ς
    2.54
     LIMITED
    2.17
     unicode
    2.02
    져
    1.96
     LOCK
    1.94
     ভাষা
    1.92
    ிய
    1.90
     limited
    1.88
     figures
    1.88
     Limited
    1.83
    Activations Density 0.000%

    No Known Activations