© 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. 70397
    Prev
    Next
    INDEX
    Explanations

    collation method

    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
    .
    -2.69
    égio
    -2.36
    一八
    -2.30
    This
    -2.19
    These
    -2.14
    あります
    -2.05
    二百
    -2.03
    But
    -2.02
    спомина
    -2.02
    ulaires
    -2.00
    POSITIVE LOGITS
     '
    2.38
    他没有
    2.28
     również
    2.28
    釭
    2.17
    9
    2.17
     shattering
    2.14
    礴
    2.09
    킁
    2.08
    老婆
    2.06
    5
    2.06
    Activations Density 0.024%

    No Known Activations