© 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. 35794
    Prev
    Next
    INDEX
    Explanations

    firefighters, celebration, climate concern

    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
     <
    0.54
     this
    0.46
     {
    0.46
     Cannot
    0.43
     ಬ
    0.42
     LEE
    0.41
    应该
    0.40
     '='
    0.40
     __
    0.40
     podcast
    0.40
    POSITIVE LOGITS
     incênd
    0.54
    消防
    0.53
     celebrar
    0.51
     voed
    0.51
     atletas
    0.50
     conservación
    0.49
     firefighters
    0.48
     daños
    0.47
     celebración
    0.47
     kebakaran
    0.47
    Activations Density 0.021%

    No Known Activations