© 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. 162078
    Prev
    Next
    INDEX
    Explanations

    producing a result

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

    specific phrases like after "EMPLOY", "INVEST", "STOCK"

    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
     therapy
    0.51
     \&
    0.50
     importe
    0.47
     Ét
    0.47
     potting
    0.47
     Punjabi
    0.46
     pât
    0.46
     steril
    0.45
     ceramic
    0.45
     Ferenc
    0.45
    POSITIVE LOGITS
    EMPLOY
    0.59
    BACKGROUND
    0.50
     سایت
    0.49
     ದಾಖ
    0.49
    OPTIONS
    0.48
    Người
    0.48
    靝
    0.48
    جیب
    0.47
    Во
    0.47
    pflicht
    0.47
    Activations Density 0.001%

    No Known Activations