© 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. 66047
    Prev
    Next
    INDEX
    Explanations

    alternative spellings and pronunciations

    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
    _=
    -0.91
     those
    -0.90
     not
    -0.88
     последу
    -0.87
    )":
    -0.84
    M
    -0.84
    johns
    -0.84
     these
    -0.82
     this
    -0.82
     M
    -0.82
    POSITIVE LOGITS
    ítica
    1.00
    PARTMENT
    1.00
    ครื่อง
    0.99
    Szer
    0.98
    ViewInit
    0.97
     dimin
    0.96
    Lähde
    0.96
     edific
    0.95
    Enllaces
    0.94
    Ahol
    0.94
    Activations Density 0.042%

    No Known Activations