© 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. 22-GEMMASCOPE-RES-131K
    7. 69216
    Prev
    Next
    INDEX
    Explanations

    tail or Taylor

    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_22/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
    ↵↵
    -3.81
    ↵
    -2.89
    "
    -2.45
    ’
    -2.44
     ambayo
    -2.36
    .’
    -2.33
    錞
    -2.31
     —
    -2.27
    迨
    -2.25
    之后的
    -2.22
    POSITIVE LOGITS
    牁
    2.89
     the
    2.75
    旆
    2.53
    зывают
    2.48
    you
    2.48
    骉
    2.47
    ⚋
    2.42
    鸲
    2.36
    ጪ
    2.36
    𓆜
    2.31
    Activations Density 0.012%

    No Known Activations