© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7096
    Prev
    Next
    INDEX
    Explanations

    technical terms and specific nouns

    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
    Транспорт
    -1.19
    owany
    -1.11
    ⇾
    -1.10
    函館
    -1.06
     위해
    -1.05
     INCOR
    -1.01
    Vel
    -1.00
    缭
    -1.00
    大きな
    -0.99
    昨日
    -0.99
    POSITIVE LOGITS
     this
    1.42
     that
    1.20
     most
    1.16
     usually
    1.13
     probably
    1.10
    zden
    1.09
     suitable
    1.07
     such
    1.06
     only
    1.05
     acontecer
    1.04
    Activations Density 0.181%

    No Known Activations