© 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. 28649
    Prev
    Next
    INDEX
    Explanations

    PRIMARY AUTO increment

    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
     on
    -1.69
     in
    -1.67
    ですが
    -1.53
    もあって
    -1.39
    を
    -1.34
     réputation
    -1.34
     also
    -1.30
    もある
    -1.27
    もありますが
    -1.26
    だが
    -1.25
    POSITIVE LOGITS
    ことも
    1.57
    為に
    1.52
     grij
    1.42
     beschä
    1.38
    ままで
    1.38
    ␻
    1.35
    を探す
    1.34
     wezen
    1.33
     comienzan
    1.31
    つづく
    1.30
    Activations Density 0.040%

    No Known Activations