© 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
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14966
    Prev
    Next
    INDEX
    Explanations

    left subtree direction

    np_acts-logits-general · gemini-2.5-flash-lite

    tree structures and operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tireless
    0.46
    厰
    0.45
    ਕਰ
    0.44
     veiled
    0.44
    綢
    0.43
    㳳
    0.42
    ارات
    0.41
    البات
    0.41
     Pilgr
    0.41
     marin
    0.41
    POSITIVE LOGITS
     Left
    0.51
    subtree
    0.50
     left
    0.48
     LEFT
    0.48
    ance
    0.47
    left
    0.47
     বাম
    0.47
    agricultural
    0.47
    leftChild
    0.46
    左
    0.46
    Activations Density 0.021%

    No Known Activations