© 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. 10-GEMMASCOPE-RES-131K
    4. 39206
    Prev
    Next
    INDEX
    Explanations

    also, will, or, only

    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
     rápidos
    -1.50
     dirigentes
    -1.38
    arture
    -1.36
    timberland
    -1.34
     competitivos
    -1.34
     Muito
    -1.26
    lumber
    -1.26
    yyv
    -1.25
     их
    -1.25
     antigo
    -1.24
    POSITIVE LOGITS
     also
    1.73
    5
    1.45
    3
    1.42
     will
    1.40
     or
    1.38
    2
    1.30
    6
    1.23
     भी
    1.22
     only
    1.21
     також
    1.20
    Activations Density 0.063%

    No Known Activations