© 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. 11230
    Prev
    Next
    INDEX
    Explanations

    code request or exception handling

    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
     from
    -1.40
     for
    -1.32
     each
    -1.30
     more
    -1.30
     aDecoder
    -1.16
     later
    -1.09
     睡
    -1.09
     a
    -1.06
     Each
    -1.05
    erals
    -0.99
    POSITIVE LOGITS
     requerida
    1.20
    jando
    1.18
    鲫
    1.17
    极其
    1.11
    因为他
    1.10
    それだけ
    1.09
    kenen
    1.09
    Hoje
    1.09
    可谓
    1.08
    太过
    1.06
    Activations Density 0.000%

    No Known Activations