© 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. 109281
    Prev
    Next
    INDEX
    Explanations

    dispose() method and components

    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
     olmayan
    -0.82
     }}=
    -0.81
    tować
    -0.77
    })=
    -0.77
     both
    -0.77
     none
    -0.76
    ElementAt
    -0.74
    '][
    -0.73
    šanās
    -0.72
    诽
    -0.72
    POSITIVE LOGITS
     disposing
    1.27
    disposing
    1.20
     disposed
    1.20
    components
    1.04
     components
    1.00
     dispose
    0.95
     disposal
    0.93
    mantec
    0.91
    flasche
    0.84
    Disposed
    0.82
    Activations Density 0.002%

    No Known Activations