© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 32418
    Prev
    Next
    INDEX
    Explanations

    github.com / en-us

    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_262k_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
    _
    0.65
     was
    0.58
     with
    0.57
     by
    0.57
     of
    0.54
    0
    0.53
    \
    0.51
    "
    0.50
    url
    0.49
     |
    0.46
    POSITIVE LOGITS
    TextViewStyle
    0.45
    ውነተኛ
    0.43
    ቸውን
    0.43
    ㏄
    0.43
    RestorePolicy
    0.42
    QAry
    0.41
    featuresMatrix
    0.41
    StockDel
    0.41
    <unused1687>
    0.41
    tcpHeader
    0.40
    Activations Density 0.011%

    No Known Activations