© 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. 84226
    Prev
    Next
    INDEX
    Explanations

    CHECK following colon

    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
     this
    -1.64
     their
    -1.47
     most
    -1.37
     an
    -1.30
     any
    -1.28
     gaining
    -1.28
     creating
    -1.20
     seeking
    -1.20
     causing
    -1.16
     fierce
    -1.15
    POSITIVE LOGITS
     certamente
    1.35
     praticamente
    1.32
     gewor
    1.26
     nimmer
    1.25
     strikingly
    1.25
    这里
    1.23
     emplo
    1.23
     показывает
    1.23
    ană
    1.23
    worfen
    1.23
    Activations Density 0.036%

    No Known Activations