© 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. 71545
    Prev
    Next
    INDEX
    Explanations

    strategy, accounts, ranks, sessions, game texts

    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
    selben
    -1.66
     creato
    -1.45
     andere
    -1.43
    Energie
    -1.37
     diing
    -1.35
     kommende
    -1.33
    滏
    -1.30
    worden
    -1.30
    ]==
    -1.29
     bílé
    -1.28
    POSITIVE LOGITS
     even
    2.16
     especially
    1.94
     may
    1.55
     jeśli
    1.48
     даже
    1.48
     only
    1.46
     is
    1.45
    D
    1.45
    even
    1.45
    d
    1.41
    Activations Density 0.125%

    No Known Activations