© 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. 120042
    Prev
    Next
    INDEX
    Explanations

    OC abbreviations and identifiers

    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
     Their
    -2.59
    ,"
    -2.30
    珢
    -2.25
     内衣
    -2.17
     駅前
    -2.13
    C
    -2.08
    盞
    -2.08
    anément
    -2.05
    藹
    -2.05
    ....
    -2.03
    POSITIVE LOGITS
    ↵
    2.61
    鱟
    2.20
    r
    2.16
     è
    2.13
    版的
    2.06
    珝
    2.05
    𓍊
    2.05
    ?)
    2.05
     has
    1.99
     “
    1.98
    Activations Density 0.005%

    No Known Activations