© 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. 14682
    Prev
    Next
    INDEX
    Explanations

    Is there a/anything/something

    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
    arts
    1.73
     xsi
    1.72
     사항
    1.65
     निर्णया
    1.64
    됩니다
    1.64
     \&
    1.63
    권을
    1.62
     Labels
    1.61
    럿
    1.57
    음을
    1.57
    POSITIVE LOGITS
    ங்கிணை
    2.03
    ोत्तम
    2.03
    ശ്വാ
    1.87
    igo
    1.83
    சி
    1.82
    ргани
    1.80
     scur
    1.76
    Figura
    1.76
    verz
    1.73
    نګ
    1.73
    Activations Density 0.000%

    No Known Activations