© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 131834
    Prev
    Next
    INDEX
    Explanations

    ghost and related concepts

    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_40_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
     InputListener
    0.45
     дерев
    0.44
     地址
    0.43
     señala
    0.43
    doll
    0.42
     doll
    0.40
    ದಾ
    0.40
    컨
    0.40
     arbor
    0.39
     popolare
    0.39
    POSITIVE LOGITS
     Ghost
    0.79
    Ghost
    0.73
     ghost
    0.72
     ghosts
    0.70
    ghost
    0.70
     Ghosts
    0.65
     ghostly
    0.60
    Ghosts
    0.56
    鬼
    0.55
    phantom
    0.54
    Activations Density 0.003%

    No Known Activations