© 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-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-16K
    4. 586
    Prev
    Next
    INDEX
    Explanations

    detailed forms and explanations

    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_9_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
    ن
    3.21
     coprime
    2.66
     soliton
    2.63
    𝘣
    2.63
    νες
    2.61
    好处
    2.58
    𝘬
    2.56
    𝘈
    2.56
    ায়ত্ত
    2.46
    𝘴
    2.45
    POSITIVE LOGITS
     gráfica
    3.15
    و
    3.12
    शील
    3.00
    লা
    2.82
    Forbes
    2.67
     사항
    2.54
    textField
    2.44
     cual
    2.39
    deg
    2.37
    де
    2.34
    Activations Density 2.476%

    No Known Activations