© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85059
    Prev
    Next
    INDEX
    Explanations

    quoted text or titles

    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
     various
    -1.32
     flere
    -1.16
     more
    -1.15
     kuris
    -1.12
     PropertyChanged
    -1.11
    ('
    -1.11
    但
    -1.08
     several
    -1.06
     серпня
    -1.04
    但是
    -1.03
    POSITIVE LOGITS
    USTOM
    1.28
     delicada
    1.25
     svoje
    1.23
     there
    1.22
     amizade
    1.22
    悻
    1.21
    licet
    1.20
    一方で
    1.17
     cometer
    1.17
     croit
    1.16
    Activations Density 0.204%

    No Known Activations