© 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-65K
    7. 3863
    Prev
    Next
    INDEX
    Explanations

    horror films

    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_65k_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
     빅뱅
    0.51
     traceability
    0.45
     উচ্ছ
    0.44
    英雄
    0.44
     бясплат
    0.44
    🏄
    0.43
     경제
    0.43
     کمان
    0.43
    浃
    0.43
     surfboard
    0.43
    POSITIVE LOGITS
     eerie
    1.74
     creepy
    1.58
     ominous
    1.48
     spooky
    1.45
     sinister
    1.39
     horror
    1.38
     paranormal
    1.37
     supernatural
    1.35
     haunted
    1.30
     mysterious
    1.24
    Activations Density 0.589%

    No Known Activations