© 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. 61226
    Prev
    Next
    INDEX
    Explanations

    it'll, you'll, i'll

    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
    텃
    -2.36
    寕
    -2.30
    𓆟
    -2.23
     returns
    -2.23
     娜
    -2.17
    -"
    -2.16
     pulls
    -2.14
     was
    -2.13
     tries
    -2.08
     proves
    -2.08
    POSITIVE LOGITS
    ?”
    2.72
     “
    2.44
    ”:
    2.20
    :”
    2.17
    cabec
    2.03
     Then
    2.02
    ENTIALS
    2.00
    猡
    1.98
    <<<<<<<
    1.96
    !”
    1.95
    Activations Density 0.011%

    No Known Activations