© 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. 67862
    Prev
    Next
    INDEX
    Explanations

    titles of albums and other media

    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
     they
    -1.51
     considerare
    -1.34
     scegliere
    -1.31
     Siehe
    -1.30
    প্র
    -1.27
     disregarding
    -1.26
     either
    -1.26
     überprü
    -1.24
     ними
    -1.23
    établir
    -1.22
    POSITIVE LOGITS
     also
    1.34
     autre
    1.33
     amitié
    1.28
     for
    1.24
     canadienne
    1.23
     people
    1.17
     aussi
    1.09
     preocupación
    1.07
     parfüm
    1.05
     in
    1.05
    Activations Density 0.278%

    No Known Activations