© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 195875
    Prev
    Next
    INDEX
    Explanations

    eat, and utensils

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

    consciousness and its opposite

    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
    journey
    0.43
    approx
    0.43
    ва
    0.42
    땜
    0.42
    між
    0.42
    نما
    0.41
     Duct
    0.40
    ত্ব
    0.39
    㕣
    0.38
    يط
    0.38
    POSITIVE LOGITS
     mencion
    0.52
     mencionados
    0.49
     cing
    0.47
    𝓛
    0.46
     ಕೆ
    0.46
     המת
    0.46
     để
    0.45
     eri
    0.45
     sympathize
    0.45
    ເພື່ອ
    0.45
    Activations Density 0.001%

    No Known Activations