© 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. 62913
    Prev
    Next
    INDEX
    Explanations

    metaphysical realm

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

    skeletal remains and ruins

    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
     shoved
    0.53
     shoving
    0.52
     shove
    0.48
     enjoined
    0.46
    K
    0.46
     DIFF
    0.45
    কো
    0.43
    enzie
    0.42
    كان
    0.41
     concurred
    0.41
    POSITIVE LOGITS
    밖
    0.55
    bserv
    0.52
     폐
    0.52
    า
    0.50
    ে
    0.48
     لیگ
    0.48
    ผู้ชมในสนาม
    0.47
     Nxd
    0.47
    引き
    0.47
    DomainMask
    0.47
    Activations Density 0.000%

    No Known Activations