© 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. 79876
    Prev
    Next
    INDEX
    Explanations

    specific contexts or actions

    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
     gyvento
    -1.30
     encender
    -1.30
     スイーツ
    -1.16
    vgili
    -1.16
     cortar
    -1.09
    Probl
    -1.07
    よろしく
    -1.07
    ğlık
    -1.06
    jarah
    -1.05
     navigazione
    -1.05
    POSITIVE LOGITS
    _
    1.13
    for
    1.08
    ur
    1.06
    ens
    1.06
    em
    1.05
    if
    1.02
    on
    1.02
    ss
    1.02
    必要がある
    1.02
    at
    0.99
    Activations Density 0.048%

    No Known Activations