© 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. 72188
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and code

    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
     retten
    -1.13
     Europas
    -1.03
    вши
    -0.95
    itys
    -0.92
    opropyl
    -0.90
     Emmanuel
    -0.90
    眠
    -0.90
    gambarkan
    -0.89
    ге
    -0.88
    itisation
    -0.87
    POSITIVE LOGITS
    בים
    1.11
    ilumin
    1.03
     needed
    1.02
    ᱕
    1.02
     seharusnya
    1.01
     gewährle
    0.99
     gewä
    0.98
     your
    0.98
     mascarilla
    0.97
    想要的
    0.96
    Activations Density 0.009%

    No Known Activations