© 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. 1856
    Prev
    Next
    INDEX
    Explanations

    bonus points

    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
    t
    -2.02
    d
    -1.64
    b
    -1.62
    i
    -1.52
    g
    -1.50
    …
    -1.46
    1
    -1.41
    The
    -1.38
    c
    -1.38
     with
    -1.37
    POSITIVE LOGITS
    genodigd
    2.22
    gangss
    1.83
    鹋
    1.73
    觧
    1.73
    beim
    1.72
    赑
    1.70
    ﮦ
    1.68
    鱨
    1.63
    fotograf
    1.63
    饪
    1.59
    Activations Density 0.013%

    No Known Activations