© 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. 203546
    Prev
    Next
    INDEX
    Explanations

    james cameron's avatar

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

    Satan as a symbol or dangerous quest

    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
     OF
    0.52
     HUD
    0.48
     Mafia
    0.47
     pronto
    0.46
    т
    0.45
     mafia
    0.45
     COMO
    0.45
     puso
    0.44
     Jude
    0.44
     OFFER
    0.44
    POSITIVE LOGITS
    ９
    0.49
    ۹
    0.48
    ５
    0.48
    㑅
    0.46
    ণ্
    0.45
    ၂
    0.45
     संयोजन
    0.45
     চিন্ত
    0.44
     సంవత్సర
    0.43
    忽视
    0.43
    Activations Density 0.000%

    No Known Activations