© 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. 22-GEMMASCOPE-RES-131K
    7. 65475
    Prev
    Next
    INDEX
    Explanations

    programming keywords and declarations

    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_22/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
     \
    -1.23
    4
    -1.17
    7
    -1.12
    _
    -1.11
    9
    -1.07
     poteva
    -1.05
    3
    -1.04
     venne
    -1.04
    6
    -1.03
    5
    -1.02
    POSITIVE LOGITS
     líqu
    1.34
     vermelhas
    1.22
     listes
    1.19
     brancas
    1.13
     dévelo
    1.11
     of
    1.11
     textes
    1.10
     competitivos
    1.08
     colonnes
    1.08
    pasar
    1.08
    Activations Density 0.004%

    No Known Activations