© 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. 117097
    Prev
    Next
    INDEX
    Explanations

    structured or coded sequences

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

    "departing from" or "departing"

    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
     throws
    0.57
    6
    0.54
     outpost
    0.53
    s
    0.53
     civil
    0.51
    t
    0.50
    4
    0.48
    `
    0.48
     group
    0.47
    p
    0.45
    POSITIVE LOGITS
     รี
    0.59
     નવી
    0.55
     السوق
    0.53
    朿
    0.53
    ︱
    0.52
     ソフト
    0.52
    籵
    0.52
     الارد
    0.51
     verhindert
    0.49
    τρα
    0.48
    Activations Density 0.001%

    No Known Activations