© 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. 29-GEMMASCOPE-2-RES-65K
    7. 5092
    Prev
    Next
    INDEX
    Explanations

    formal language

    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
    、
    0.86
    %、
    0.82
     seventy
    0.80
     、
    0.78
     seven
    0.77
    ”、
    0.76
     Thursday
    0.76
    )、
    0.73
     since
    0.73
     jeudi
    0.73
    POSITIVE LOGITS
        
    2.32
         
    1.21
       
    0.92
    Só
    0.85
    Sous
    0.78
    Although
    0.78
    Boa
    0.77
    <0x8A>
    0.77
    bindingNavigator
    0.77
    બો
    0.76
    Activations Density 0.651%

    No Known Activations