© 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. 70767
    Prev
    Next
    INDEX
    Explanations

    citations and references

    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
    OCO
    -0.97
     from
    -0.89
    ?)
    -0.86
     Осо
    -0.84
    ndale
    -0.84
    orphism
    -0.81
    žití
    -0.79
     their
    -0.78
     cucchiai
    -0.77
     both
    -0.77
    POSITIVE LOGITS
     again
    0.90
    🡪
    0.87
    を
    0.79
     الكه
    0.77
     هنا
    0.77
     here
    0.75
    Odpo
    0.74
    drei
    0.73
    말
    0.72
    cetype
    0.71
    Activations Density 0.003%

    No Known Activations