© 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. 67857
    Prev
    Next
    INDEX
    Explanations

    coming into or to

    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
    O
    -1.34
     wystar
    -1.34
    細かく
    -1.31
    未だ
    -1.31
    D
    -1.30
    知っている
    -1.30
    つづく
    -1.30
    どれだけ
    -1.25
     lichaam
    -1.23
    行
    -1.23
    POSITIVE LOGITS
     with
    1.56
     by
    1.41
    Especificación
    1.41
     of
    1.41
    Especificaciones
    1.37
    ALLENGES
    1.34
    banken
    1.33
    phonie
    1.30
    МП
    1.30
     banjir
    1.30
    Activations Density 0.041%

    No Known Activations