© 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. 22-GEMMASCOPE-2-RES-16K
    7. 10874
    Prev
    Next
    INDEX
    Explanations

    NAMI contact information

    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_22_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
    𒊩
    1.71
    𒄭
    1.64
    𐰼
    1.64
    Ⲇ
    1.63
    𐰣
    1.57
    avkhat
    1.56
    𒋀
    1.56
    𒌆
    1.55
    𒆪
    1.55
     threx
    1.53
    POSITIVE LOGITS
     AA
    1.07
     P
    1.06
    0.99
     S
    0.99
     M
    0.92
     mm
    0.90
     W
    0.89
    <eos>
    0.89
     /
    0.88
     p
    0.87
    Activations Density 0.096%

    No Known Activations