© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 4410
    Prev
    Next
    INDEX
    Explanations

    recent past actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    o
    0.54
    old
    0.52
    ER
    0.52
    one
    0.51
    H
    0.50
     that
    0.48
    OLD
    0.48
    a
    0.48
     agad
    0.47
    1
    0.47
    POSITIVE LOGITS
     recientemente
    1.18
     lately
    1.16
     منذ
    1.09
     recentemente
    1.09
     récemment
    1.08
     since
    1.05
     Lately
    1.05
    近年来
    1.00
     Since
    0.98
     최근
    0.98
    Activations Density 0.203%

    No Known Activations