© 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. 57413
    Prev
    Next
    INDEX
    Explanations

    protecting, prospects, water, standard

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

    ** or ( followed by description

    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
    chant
    0.48
    кро
    0.48
    했지만
    0.47
     хотелось
    0.46
     evitando
    0.46
    }<\
    0.45
    hexagon
    0.45
     желания
    0.44
     ইচ্ছ
    0.44
     ઇચ્છ
    0.44
    POSITIVE LOGITS
     Sky
    0.50
    役
    0.48
    载
    0.45
     sky
    0.44
     Clothing
    0.42
     Backpack
    0.42
     Boot
    0.42
     Wireless
    0.41
     This
    0.41
    Sky
    0.41
    Activations Density 0.000%

    No Known Activations