© 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. 1436
    Prev
    Next
    INDEX
    Explanations

    numerical values and calculations

    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
    OnFileChange
    0.28
    禳
    0.26
     கற்ற
    0.25
    BleStatus
    0.25
    BeforeText
    0.24
    沍
    0.24
    EndX
    0.24
    BySize
    0.23
    MyToolkit
    0.23
    ProductsStore
    0.23
    POSITIVE LOGITS
    ↵
    0.36
    5
    0.35
     was
    0.30
    er
    0.28
     com
    0.28
     sand
    0.28
     billion
    0.28
    m
    0.28
     j
    0.27
    ie
    0.27
    Activations Density 0.225%

    No Known Activations