© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 1057
    Prev
    Next
    INDEX
    Explanations

    boolean values true/false

    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_all/layer_41_width_262k_l0_big
    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
    ROTTLE
    0.62
    ួរ
    0.61
    ُو
    0.60
    OLYBD
    0.59
    IRCONIUM
    0.57
    ้ำ
    0.57
    ِد
    0.55
    液
    0.55
    <0x94>
    0.55
    ionicons
    0.54
    POSITIVE LOGITS
     false
    1.46
     true
    1.45
     True
    1.41
     False
    1.38
     TRUE
    1.32
    true
    1.25
    True
    1.25
    false
    1.25
    False
    1.24
     FALSE
    1.20
    Activations Density 0.014%

    No Known Activations