© 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. 23809
    Prev
    Next
    INDEX
    Explanations

    scholastic reworkings of doctrinal material

    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
    правка
    -0.79
    NX
    -0.78
    Così
    -0.77
     awkwardly
    -0.74
    NodeList
    -0.73
    zando
    -0.73
    ᚋ
    -0.73
     piedras
    -0.71
    SECT
    -0.71
     Timber
    -0.71
    POSITIVE LOGITS
     Trolley
    0.82
    errorMsg
    0.76
    rtc
    0.70
     tudom
    0.69
    山形
    0.69
     getTime
    0.69
     Aragon
    0.68
     coloro
    0.68
    øg
    0.68
    érie
    0.67
    Activations Density 0.002%

    No Known Activations