© 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. 73512
    Prev
    Next
    INDEX
    Explanations

    preposition followed by noun/verb

    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
     that
    -1.50
    pography
    -1.48
     abſ
    -1.26
     there
    -1.24
    馋
    -1.23
    vested
    -1.21
    の中には
    -1.18
    signable
    -1.16
    вь
    -1.13
    ilets
    -1.13
    POSITIVE LOGITS
     its
    1.80
     medesimo
    1.48
     linguaggio
    1.45
     cammino
    1.41
     on
    1.41
     their
    1.40
    我们就
    1.37
    iciaries
    1.37
     using
    1.36
     my
    1.34
    Activations Density 0.169%

    No Known Activations