© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 45224
    Prev
    Next
    INDEX
    Explanations

    licensed and made available

    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
    maan
    -0.76
    ук
    -0.75
    efes
    -0.75
     venir
    -0.74
    amet
    -0.73
    šn
    -0.73
    ниш
    -0.73
     removable
    -0.73
    byteArray
    -0.73
    assertRaises
    -0.72
    POSITIVE LOGITS
     affrontare
    0.87
     pisau
    0.87
    ให้
    0.82
     choices
    0.81
    Contexte
    0.79
    んだよ
    0.77
     vacanze
    0.77
     raggiungere
    0.75
     correct
    0.74
     merkwür
    0.73
    Activations Density 0.000%

    No Known Activations