© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 113572
    Prev
    Next
    INDEX
    Explanations

    price, value, rates

    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
     diferentes
    -1.43
     teorías
    -1.37
     différents
    -1.37
    が必要です
    -1.27
     helemaal
    -1.27
     this
    -1.26
     distintas
    -1.25
     actitudes
    -1.24
    fillment
    -1.24
    が必要
    -1.24
    POSITIVE LOGITS
     oogen
    1.37
     and
    1.37
     prices
    1.28
    ?“
    1.20
    ?;
    1.20
     barcelona
    1.18
    --"
    1.18
    ??"
    1.16
    衣裙
    1.16
    ?<
    1.16
    Activations Density 0.008%

    No Known Activations