© 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. 13927
    Prev
    Next
    INDEX
    Explanations

    causes effect on me/someone

    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
     it
    -1.75
     acesta
    -1.69
     its
    -1.52
     in
    -1.41
    ",
    -1.37
     there
    -1.35
     aceasta
    -1.34
    父の
    -1.25
     this
    -1.24
     это
    -1.22
    POSITIVE LOGITS
     них
    1.51
    Mereka
    1.50
    backers
    1.44
     recomendable
    1.43
    ématiques
    1.39
     když
    1.38
    ljeno
    1.37
    𝔗
    1.37
    tonsoft
    1.36
    AuthContext
    1.36
    Activations Density 0.048%

    No Known Activations