© 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
    2. Gemma-3-1B
    3. 17-GEMMASCOPE-2-RES-16K
    4. 2508
    Prev
    Next
    INDEX
    Explanations

    storytelling and narratives

    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_17_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
     scarcely
    1.44
    although
    1.40
    
    1.39
    whose
    1.35
    described
    1.31
    牞
    1.29
     inasmuch
    1.26
     variously
    1.25
    ဟု
    1.25
     furnishes
    1.25
    POSITIVE LOGITS
     kiddos
    1.81
     alakalı
    1.63
     🙏
    1.63
    /
    1.62
     /
    1.59
     impactful
    1.57
     🔥
    1.55
     👀
    1.54
     personnes
    1.51
     ❤️
    1.49
    Activations Density 0.335%

    No Known Activations