© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 104283
    Prev
    Next
    INDEX
    Explanations

    complex or complicated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     from
    -2.02
    合わせた
    -1.59
     are
    -1.48
    -
    -1.41
    </i>
    -1.41
     similar
    -1.35
    '
    -1.35
     It
    -1.34
     as
    -1.32
     same
    -1.32
    POSITIVE LOGITS
     why
    1.67
    ㊗
    1.63
     первая
    1.63
    ፩
    1.62
     たく
    1.60
     systemu
    1.59
    儛
    1.59
     how
    1.59
     wszystkie
    1.58
    复杂的
    1.58
    Activations Density 0.046%

    No Known Activations