© 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. 54231
    Prev
    Next
    INDEX
    Explanations

    journal submissions and articles

    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
     I
    -2.27
     didn
    -2.20
     wasn
    -1.84
     people
    -1.80
     doesn
    -1.61
     my
    -1.59
     isn
    -1.58
     used
    -1.55
     it
    -1.48
     wouldn
    -1.41
    POSITIVE LOGITS
     кроссовки
    1.77
    筇
    1.66
    ÈNE
    1.63
    ggars
    1.59
    ælp
    1.54
    וּ
    1.54
    ᾿
    1.52
    cribir
    1.52
     меда
    1.52
    ־ה
    1.51
    Activations Density 0.026%

    No Known Activations