© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106718
    Prev
    Next
    INDEX
    Explanations

    starts of structured data or phrases

    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
    angkap
    -1.01
    ">“
    -1.00
    ždy
    -0.91
    Context
    -0.88
    cadi
    -0.86
    irma
    -0.85
    dison
    -0.84
    ￡
    -0.84
     excluir
    -0.84
     tuyau
    -0.84
    POSITIVE LOGITS
     milla
    0.94
    采用了
    0.92
    lal
    0.91
     außerdem
    0.91
    ⋰
    0.89
    Awkward
    0.88
     Usa
    0.88
    contd
    0.86
     rotas
    0.85
    byes
    0.84
    Activations Density 0.001%

    No Known Activations