© 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. 70731
    Prev
    Next
    INDEX
    Explanations

    date: 'Received'

    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
     both
    -1.34
     eight
    -1.18
     several
    -1.16
     wzglę
    -1.16
     because
    -1.14
     any
    -1.13
     not
    -1.09
     adorno
    -1.08
     those
    -1.08
     three
    -1.03
    POSITIVE LOGITS
     and
    1.61
    atization
    1.12
     REALLY
    1.12
    rceil
    1.10
    olving
    1.10
    mands
    1.05
    continues
    1.05
    
    1.05
    haping
    1.05
    nappropriate
    1.04
    Activations Density 0.000%

    No Known Activations