© 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-16K
    4. 517
    Prev
    Next
    INDEX
    Explanations

    "There are" followed by enumeration

    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_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
    lies
    0.74
    encias
    0.65
     मंत्रालय
    0.65
     includ
    0.59
    ries
    0.58
     logits
    0.57
     taff
    0.57
    ‴
    0.57
    elessly
    0.57
     fleeing
    0.57
    POSITIVE LOGITS
     wasn
    0.77
     Plusieurs
    0.69
     hasn
    0.67
    偣
    0.67
    여러
    0.66
    多种
    0.66
     isn
    0.66
     разных
    0.65
     bukanlah
    0.64
     разные
    0.64
    Activations Density 0.061%

    No Known Activations