© 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. 13587
    Prev
    Next
    INDEX
    Explanations

    category and references labels

    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
     is
    -1.49
    Certain
    -1.26
    甚至是
    -1.14
    ⁨
    -1.09
    umą
    -1.09
    "
    -1.09
     The
    -1.00
    ❉
    -0.99
    '
    -0.98
    🕗
    -0.96
    POSITIVE LOGITS
    (!__
    1.41
    brtc
    1.29
    霸气
    1.27
    veillance
    1.21
    ஏ
    1.20
    Modifica
    1.18
     ویت
    1.18
    蔸
    1.17
     and
    1.16
    cticut
    1.16
    Activations Density 0.006%

    No Known Activations