© 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. 117519
    Prev
    Next
    INDEX
    Explanations

    width, height, size

    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
    ayama
    -0.83
    ∣
    -0.81
     """",
    -0.79
    phäre
    -0.74
     tempio
    -0.72
    ','',
    -0.72
    utf
    -0.72
     accurate
    -0.72
    روع
    -0.69
    liğ
    -0.69
    POSITIVE LOGITS
    props
    1.13
     props
    1.13
     "
    1.11
     “
    1.06
     provavelmente
    0.94
     periódico
    0.90
     doivent
    0.90
     Medidas
    0.89
     Props
    0.88
    Props
    0.87
    Activations Density 0.001%

    No Known Activations