© 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. 28073
    Prev
    Next
    INDEX
    Explanations

    instead of

    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
     either
    -1.01
     this
    -0.96
     always
    -0.92
    Toujours
    -0.88
     both
    -0.87
    listas
    -0.85
     too
    -0.85
     could
    -0.84
     doubtless
    -0.83
    も行
    -0.83
    POSITIVE LOGITS
    ではなく
    0.97
     şekilde
    0.87
     invece
    0.86
    ykjav
    0.82
     instead
    0.81
    stdc
    0.78
    其他
    0.78
     вместо
    0.77
     Reverend
    0.76
    Pant
    0.76
    Activations Density 0.012%

    No Known Activations