© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4705
    Prev
    Next
    INDEX
    Explanations

    starting or beginning something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
     fram
    0.81
     Blind
    0.72
     mediator
    0.70
     слот
    0.70
     H
    0.68
     Ox
    0.68
     G
    0.68
     buffers
    0.67
     juj
    0.67
     sepsis
    0.66
    POSITIVE LOGITS
    inizio
    0.92
    ffen
    0.82
    ı
    0.82
    amı
    0.82
     iniziare
    0.81
    }($
    0.80
    ils
    0.79
    itzerland
    0.79
     eventful
    0.79
    ıl
    0.79
    Activations Density 0.005%

    No Known Activations