© 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. 44185
    Prev
    Next
    INDEX
    Explanations

    i.e. or es decir

    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
    Why
    -1.29
     Organisator
    -1.25
     البته
    -1.23
     also
    -1.22
    in
    -1.17
     include
    -1.16
     such
    -1.16
    t
    -1.14
     такой
    -1.13
     of
    -1.12
    POSITIVE LOGITS
    ≔
    1.38
     and
    1.35
     ſta
    1.29
     segü
    1.27
     ``
    1.27
    mêmes
    1.23
    ѳ
    1.20
     „
    1.20
    suites
    1.20
    ########.
    1.18
    Activations Density 0.119%

    No Known Activations