© 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. 102101
    Prev
    Next
    INDEX
    Explanations

    hard time

    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
     a
    -1.90
    彼らの
    -1.53
    鉿
    -1.52
     Further
    -1.43
    茄子
    -1.42
    علان
    -1.41
     Wissenschaftler
    -1.40
     schönsten
    -1.39
     Some
    -1.38
     Various
    -1.37
    POSITIVE LOGITS
     únicas
    1.67
    etc
    1.58
     exposes
    1.54
     antemano
    1.53
     endeavors
    1.45
    or
    1.45
     liknande
    1.45
     カラ
    1.43
     všetkých
    1.42
    使う
    1.41
    Activations Density 0.009%

    No Known Activations