© 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. 29-GEMMASCOPE-2-RES-65K
    4. 4702
    Prev
    Next
    INDEX
    Explanations

    alternatives connected by or

    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_29_width_65k_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
    さと
    1.14
     &&
    1.04
    ുമുള്ള
    1.03
    &&
    0.97
    ্যালেঞ্জ
    0.88
    ുണ്ട്
    0.85
    性と
    0.85
    ప్పటి
    0.84
    分别是
    0.82
    മുണ്ട്
    0.82
    POSITIVE LOGITS
     or
    7.56
     или
    7.17
    或
    7.01
     hoặc
    6.77
     atau
    6.72
     eller
    6.57
     oder
    6.45
    或者
    6.38
    หรือ
    6.36
     किंवा
    6.32
    Activations Density 4.311%

    No Known Activations