© 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. 82432
    Prev
    Next
    INDEX
    Explanations

    latent/hidden states

    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
    了
    -0.72
     Matrices
    -0.71
    礼
    -0.69
     extrem
    -0.69
    tsch
    -0.68
    zam
    -0.68
    Criterion
    -0.67
    datagrid
    -0.67
    的声音
    -0.65
     प्रतिशत
    -0.65
    POSITIVE LOGITS
     latent
    2.67
     hidden
    2.25
    latent
    2.09
    hidden
    1.74
     Hidden
    1.62
     скры
    1.60
     Latent
    1.59
    Hidden
    1.52
     states
    1.40
    Lat
    1.35
    Activations Density 0.036%

    No Known Activations