© 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. 70144
    Prev
    Next
    INDEX
    Explanations

    halogen, Wave, physics, science

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

    negation or specific qualifying words

    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
    :
    0.55
     عشر
    0.49
    δ
    0.47
    надцать
    0.46
    ön
    0.46
     लौटने
    0.45
     Magistrate
    0.45
    нями
    0.45
     версия
    0.44
    个
    0.44
    POSITIVE LOGITS
    Waves
    0.49
     Guilherme
    0.49
     نعمت
    0.47
     ئەم
    0.46
    halogen
    0.46
    lytres
    0.46
    waves
    0.45
     그럼
    0.45
     halogen
    0.45
     ಅವರ
    0.44
    Activations Density 0.000%

    No Known Activations