© 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
    5. 29-GEMMASCOPE-2-RES-16K
    7. 784
    Prev
    Next
    INDEX
    Explanations

    Do you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <start_of_image>
    1.07
    :")
    1.03
    </b>
    0.90
    :[
    0.90
    ":"
    0.90
    "):
    0.89
    :");
    0.89
    *:
    0.86
    :\\
    0.85
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.84
    POSITIVE LOGITS
     gaming
    1.06
    Gaming
    1.02
     gambling
    0.98
     gamers
    0.97
    gaming
    0.97
     Casinos
    0.96
     casinos
    0.96
    Casino
    0.95
     Gaming
    0.94
     Gambling
    0.91
    Activations Density 0.016%

    No Known Activations