© 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. 34-GEMMASCOPE-RES-131K
    7. 38576
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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_34/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
     contentment
    -0.83
    XmlAccessType
    -0.82
     linear
    -0.82
     Syst
    -0.80
     Linear
    -0.80
    ЖИ
    -0.79
     PREVIEW
    -0.78
     étude
    -0.76
    happy
    -0.76
     repose
    -0.76
    POSITIVE LOGITS
     fırs
    0.88
     belirt
    0.87
    )>=
    0.82
     Glieder
    0.82
    瞥
    0.79
    hlon
    0.78
     durumu
    0.75
     though
    0.75
    although
    0.74
    気になって
    0.73
    Activations Density 0.053%

    No Known Activations