© 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. 10-GEMMASCOPE-RES-131K
    7. 69418
    Prev
    Next
    INDEX
    Explanations

    module exports function or object

    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_10/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
    ↵↵
    -1.69
    ⚋
    -1.68
     první
    -1.49
     baseado
    -1.49
    氿
    -1.47
    をの
    -1.45
     extremamente
    -1.44
     powiedzieć
    -1.42
     kupić
    -1.41
     angefü
    -1.41
    POSITIVE LOGITS
     includes
    1.66
    💁
    1.65
     粉色
    1.59
     are
    1.58
    ，”
    1.52
     vanden
    1.47
     including
    1.46
    er
    1.42
    ickou
    1.42
     melap
    1.41
    Activations Density 0.005%

    No Known Activations