© 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. 83593
    Prev
    Next
    INDEX
    Explanations

    bottom of

    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
     top
    -1.11
    ̏
    -0.94
     oberen
    -0.91
    </td>
    -0.89
    一个小
    -0.88
    贗
    -0.87
     he
    -0.84
     backs
    -0.84
     upper
    -0.84
     çıkan
    -0.83
    POSITIVE LOGITS
    most
    1.55
    ToTop
    1.10
     dwellers
    0.96
     tier
    0.94
    logy
    0.91
    chê
    0.90
    ଃ
    0.90
     dwells
    0.89
    STRACT
    0.86
     Bottom
    0.86
    Activations Density 0.014%

    No Known Activations