© 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. 13881
    Prev
    Next
    INDEX
    Explanations

    far from / anything but

    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
     parachoque
    -1.63
    ឵
    -1.61
    somewhat
    -1.57
     preferências
    -1.56
    ჻
    -1.55
    垍
    -1.53
    และ
    -1.50
     maneiras
    -1.46
     klient
    -1.45
    蟶
    -1.45
    POSITIVE LOGITS
     being
    1.59
     have
    1.49
     They
    1.48
    </b>
    1.47
    !
    1.46
     are
    1.45
     any
    1.37
    ,
    1.31
     estamos
    1.25
    呀
    1.24
    Activations Density 0.009%

    No Known Activations