© 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. 48532
    Prev
    Next
    INDEX
    Explanations

    URLs, code imports, descriptions

    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
    اریخ
    -0.94
     COVERAGE
    -0.84
    嗮
    -0.82
     Anglican
    -0.81
    OrNull
    -0.81
     wciąż
    -0.81
     насеље
    -0.80
    динг
    -0.80
    áneamente
    -0.79
    ventions
    -0.77
    POSITIVE LOGITS
    ysuckle
    0.81
    Yn
    0.75
     commonly
    0.74
    marshaller
    0.74
     بالم
    0.73
    ícola
    0.72
    engagent
    0.72
     Дне
    0.72
     elkaar
    0.71
    Common
    0.71
    Activations Density 0.005%

    No Known Activations