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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 14454
    Prev
    Next
    INDEX
    Explanations

    less about

    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
    ाइंड
    1.78
    ufact
    1.77
    ﹰ
    1.75
     ا
    1.75
     بھارتی
    1.66
    ूब
    1.65
     ر
    1.65
     اد
    1.63
     ак
    1.63
     accuse
    1.62
    POSITIVE LOGITS
    gels
    1.71
    nate
    1.62
    saved
    1.57
    isak
    1.57
    yte
    1.45
    isal
    1.44
     saved
    1.44
    佗
    1.44
    ikti
    1.44
    message
    1.42
    Activations Density 0.002%

    No Known Activations