© 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. 72692
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and symbols

    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
     getPlayer
    -0.93
     মা
    -0.93
    șa
    -0.91
     jugadores
    -0.91
    brücken
    -0.89
     reciclaje
    -0.88
    jedi
    -0.88
    媲
    -0.88
    jobb
    -0.88
    ädigung
    -0.88
    POSITIVE LOGITS
     we
    0.97
    睒
    0.94
    जब
    0.92
    īj
    0.92
    ですから
    0.91
    meuble
    0.91
    ссор
    0.90
    ということで
    0.90
    rather
    0.89
     kacang
    0.89
    Activations Density 0.080%

    No Known Activations