© 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. 10692
    Prev
    Next
    INDEX
    Explanations

    Halloween and pumpkins

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

    Halloween and scary things

    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
    離婚
    0.47
     кушымта
    0.44
     privatization
    0.43
     uplink
    0.42
     negligently
    0.40
    쳥
    0.40
     ಪ್ರಕರಣ
    0.40
    splits
    0.39
    داول
    0.39
    藍
    0.39
    POSITIVE LOGITS
     Halloween
    1.66
    Halloween
    1.56
     halloween
    1.46
    🎃
    1.45
    halloween
    1.43
     Pumpkin
    1.21
     pumpkin
    1.19
     pumpkins
    1.18
    Pumpkin
    1.15
    alloween
    1.10
    Activations Density 0.074%

    No Known Activations