© 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. 606
    Prev
    Next
    INDEX
    Explanations

    expecting or imagining future

    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
     disagrees
    0.81
    を使って
    0.80
     confuses
    0.79
     undesired
    0.79
     unintended
    0.77
     deleting
    0.75
     hates
    0.75
    🤬
    0.75
    🤦
    0.75
    🤞
    0.75
    POSITIVE LOGITS
     Situated
    1.78
    Situated
    1.77
     Located
    1.69
    Located
    1.57
     Visitors
    1.48
     situated
    1.47
     Nearby
    1.45
    Visitors
    1.42
     located
    1.41
     Adjacent
    1.35
    Activations Density 1.055%

    No Known Activations