© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 53585
    Prev
    Next
    INDEX
    Explanations

    decreased theta waves

    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_31_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
     Waves
    0.46
     農
    0.46
    azadas
    0.46
     య
    0.45
    DISABLE
    0.45
    ismo
    0.45
    AYLOR
    0.45
    чика
    0.45
    면에
    0.44
     Barang
    0.44
    POSITIVE LOGITS
     tất
    0.40
     reality
    0.39
     sentences
    0.39
    标志
    0.39
    elt
    0.38
    ።
    0.38
     sentence
    0.37
     roaring
    0.37
     Scotts
    0.37
     transcript
    0.36
    Activations Density 0.005%

    No Known Activations