© 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. 11247
    Prev
    Next
    INDEX
    Explanations

    CSS styling properties

    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
     overflowing
    0.28
     placeholder
    0.28
    高さ
    0.28
     tete
    0.27
    姓
    0.26
     slou
    0.26
    的高度
    0.25
     втори
    0.25
     ليس
    0.25
     }{}_{\
    0.25
    POSITIVE LOGITS
    Subjects
    0.29
    راء
    0.28
    subjects
    0.27
    aisen
    0.27
    jar
    0.27
    lev
    0.26
    rainbow
    0.26
    bergs
    0.26
    leich
    0.26
    Delhi
    0.26
    Activations Density 0.055%

    No Known Activations