© 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. 16406
    Prev
    Next
    INDEX
    Explanations

    Poo Big Chungus currency Vertex

    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
     Gasoline
    0.38
     Kin
    0.36
     Patience
    0.35
    బర్
    0.35
    뭇
    0.35
     Wiggins
    0.34
     TOD
    0.34
     widest
    0.34
     Hodges
    0.34
     Schall
    0.33
    POSITIVE LOGITS
    liter
    0.41
     สร้าง
    0.41
    藠
    0.40
     літера
    0.39
     литератур
    0.39
     فائدہ
    0.39
     cruising
    0.38
    ফতরের
    0.38
     वैरिएंट
    0.38
    Vertex
    0.38
    Activations Density 0.002%

    No Known Activations