© 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. 10-GEMMASCOPE-RES-131K
    7. 61500
    Prev
    Next
    INDEX
    Explanations

    sequence prediction

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron remains inactive on all the shown tokens, so it does not detect any pattern in these excerpts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    }(
    -1.69
     time
    -1.67
    euvres
    -1.65
     won
    -1.64
     said
    -1.63
     decided
    -1.63
     years
    -1.60
    <td>
    -1.57
     since
    -1.57
     spent
    -1.56
    POSITIVE LOGITS
    s
    2.89
    なぜか
    1.97
    t
    1.79
    l
    1.73
    などに
    1.71
    n
    1.66
    めちゃくちゃ
    1.66
    めっちゃ
    1.65
    tain
    1.63
    en
    1.62
    Activations Density 0.002%

    No Known Activations