© 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. 2539
    Prev
    Next
    INDEX
    Explanations

    start of question

    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
    ~$
    -0.70
     Dead
    -0.69
    消失
    -0.68
    annual
    -0.68
    広島
    -0.65
    PictureBox
    -0.65
    Пре
    -0.65
     distribuir
    -0.64
    amat
    -0.64
    jane
    -0.64
    POSITIVE LOGITS
     bewer
    0.68
    uteen
    0.68
    xz
    0.64
     inscrit
    0.63
     pulmonary
    0.63
    ₆
    0.63
    wara
    0.63
    選挙
    0.63
    minyak
    0.62
    thritis
    0.61
    Activations Density 0.226%

    No Known Activations