© 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. 54120
    Prev
    Next
    INDEX
    Explanations

    surprising context or explanation

    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
    FORME
    -0.86
    роде
    -0.82
     minera
    -0.81
     zwar
    -0.81
    ró
    -0.81
     ゼ
    -0.80
    ུ
    -0.80
    ieke
    -0.79
    EDOM
    -0.79
    tedy
    -0.79
    POSITIVE LOGITS
     given
    6.44
     considering
    5.47
    given
    4.75
    Given
    4.72
     Given
    4.56
    considering
    3.89
    Considering
    3.89
     Considering
    3.78
     GIVEN
    3.61
     учиты
    3.52
    Activations Density 0.283%

    No Known Activations