© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 74806
    Prev
    Next
    INDEX
    Explanations

    check and uncheck actions

    np_acts-logits-general · gemini-2.5-flash-lite

    uncommenting or commenting out blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    𝐭
    0.41
     जिनसे
    0.40
     सहायता
    0.38
     Safegu
    0.37
     प्राइवेट
    0.37
     Potatoes
    0.37
     Accountability
    0.36
     تمہیں
    0.36
     Instances
    0.35
    ति
    0.35
    POSITIVE LOGITS
     runways
    0.45
     catwalk
    0.45
     trough
    0.43
    ⇤
    0.43
    selected
    0.43
     bijective
    0.43
     synthet
    0.43
     有
    0.42
     selected
    0.42
    quinoline
    0.42
    Activations Density 0.001%

    No Known Activations