© 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. 87012
    Prev
    Next
    INDEX
    Explanations

    citation brackets 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
    theatre
    -1.07
     when
    -1.03
     if
    -0.94
     kunjung
    -0.94
     by
    -0.93
    charlie
    -0.91
     where
    -0.90
     or
    -0.90
    floors
    -0.89
    pineapple
    -0.88
    POSITIVE LOGITS
    <h3>
    1.09
     않습니다
    1.06
     hugely
    0.98
    <h1>
    0.96
     смы
    0.95
     tumultuous
    0.94
    ността
    0.94
    ો
    0.94
     سپاه
    0.94
    <h2>
    0.93
    Activations Density 0.054%

    No Known Activations