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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 13953
    Prev
    Next
    INDEX
    Explanations

    string replacement and slashes

    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
    enças
    0.44
     convincingly
    0.44
    rum
    0.41
    fasta
    0.40
    ើម
    0.39
     நிர்வாகிகள்
    0.39
     وقلنا
    0.38
    纜
    0.38
    覺得
    0.38
    ോഗ
    0.38
    POSITIVE LOGITS
    بة
    0.45
    䡇
    0.41
     volled
    0.40
     petroleum
    0.38
     بر
    0.38
    يلات
    0.38
     entirety
    0.38
     volledig
    0.38
     poprzez
    0.37
     afbeelding
    0.37
    Activations Density 0.017%

    No Known Activations