© 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-262K
    7. 101437
    Prev
    Next
    INDEX
    Explanations

    gas station, critical, true, crucial

    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_262k_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
    F
    0.60
    X
    0.57
    H
    0.55
    W
    0.52
    U
    0.52
    V
    0.50
    xadmin
    0.50
    N
    0.49
    R
    0.47
    gew
    0.47
    POSITIVE LOGITS
     epiph
    0.48
     diverg
    0.47
     jika
    0.46
     divergents
    0.46
     forêt
    0.44
     pono
    0.43
     degrés
    0.43
     vigilance
    0.43
     étude
    0.42
    磴
    0.41
    Activations Density 0.003%

    No Known Activations