© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 15638
    Prev
    Next
    INDEX
    Explanations

    CT scans, iOS widgets, estimated around

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     haberse
    1.45
    겅
    1.25
     dor
    1.25
    แข่ง
    1.21
    قة
    1.20
     época
    1.12
     helst
    1.11
     maternelle
    1.10
     vâr
    1.09
     competencias
    1.09
    POSITIVE LOGITS
    h
    1.26
    alien
    1.11
    ѕ
    1.11
    임
    1.08
    в
    1.01
    ти
    0.99
    אות
    0.99
    א
    0.96
    extended
    0.96
    多的
    0.96
    Activations Density 0.003%

    No Known Activations