© 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. 75251
    Prev
    Next
    INDEX
    Explanations

    persistence and versioning

    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
     {
    -2.92
    of
    -2.81
    -2.66
     avec
    -2.64
    -2.63
     They
    -2.44
    2
    -2.42
     the
    -2.42
    on
    -2.39
    with
    -2.28
    POSITIVE LOGITS
    ”،
    2.55
    涐
    2.34
    曏
    2.33
    到这里
    2.25
     apparaat
    2.19
    我们要
    2.19
    <bos>
    2.16
    勍
    2.06
     occaf
    2.02
    𝕲
    2.02
    Activations Density 0.003%

    No Known Activations