© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 54269
    Prev
    Next
    INDEX
    Explanations

    too far or too much

    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_22/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
    
    -1.48
     trám
    -1.43
    ſſen
    -1.38
     ocorrer
    -1.29
     durabilidad
    -1.23
     quí
    -1.22
    .
    -1.21
     NÃO
    -1.21
    jours
    -1.20
     (
    -1.19
    POSITIVE LOGITS
     when
    1.51
     after
    1.34
    일에
    1.30
    🤙
    1.27
    🤘
    1.27
     because
    1.25
    😤
    1.25
     as
    1.25
     while
    1.23
    🤭
    1.23
    Activations Density 0.062%

    No Known Activations