© 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. 22-GEMMASCOPE-RES-131K
    7. 71418
    Prev
    Next
    INDEX
    Explanations

    originating or coming from

    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
    for
    -1.07
     irmã
    -1.06
    milli
    -1.00
    ᨁ
    -1.00
     breathtaking
    -0.99
     wavelength
    -0.96
     sämtliche
    -0.94
    atchi
    -0.94
     offer
    -0.94
    xing
    -0.94
    POSITIVE LOGITS
     from
    1.17
     into
    1.09
    Ciri
    1.07
     anise
    1.02
    닮
    1.00
    ća
    0.96
    ("").
    0.95
    Vaccination
    0.93
    nimi
    0.93
     dialami
    0.89
    Activations Density 0.074%

    No Known Activations