© 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. 13-GEMMASCOPE-2-RES-16K
    4. 9054
    Prev
    Next
    INDEX
    Explanations

    health topics

    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_13_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
     श्रीनगर
    1.20
    ogas
    1.20
     diverting
    1.16
    ah
    1.15
    ंगी
    1.15
    妨
    1.15
     finalement
    1.13
     recuper
    1.11
    供
    1.11
    期間限定
    1.10
    POSITIVE LOGITS
     άνθρω
    1.46
     ডিপ
    1.20
    ี่ยว
    1.16
    롱
    1.13
     কর্মকর্তা
    1.12
     billions
    1.11
    ンダント
    1.08
     الإنسان
    1.08
     MPP
    1.07
     Fund
    1.06
    Activations Density 0.000%

    No Known Activations