© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 6107
    Prev
    Next
    INDEX
    Explanations

    Google DeepMind Gemma

    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
    
    2.71
    $)
    2.53
    ার
    2.45
    
    2.40
     havoc
    2.38
    
    2.32
    er
    2.31
    erun
    2.28
    erad
    2.27
     heatmap
    2.25
    POSITIVE LOGITS
    ج
    3.05
    प
    2.67
    ਲ
    2.45
    লি
    2.42
    ERS
    2.39
    म
    2.39
    س
    2.35
    로
    2.32
    accompan
    2.22
    मा
    2.16
    Activations Density 0.052%

    No Known Activations