© 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. 55755
    Prev
    Next
    INDEX
    Explanations

    `key` or `tag`

    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
     หน
    -0.84
    drav
    -0.77
     KINGDOM
    -0.75
    onee
    -0.74
     preparing
    -0.74
    élève
    -0.73
     Euri
    -0.71
    rull
    -0.70
     bensin
    -0.69
    َب
    -0.69
    POSITIVE LOGITS
    NBT
    1.03
     tag
    1.02
     tags
    0.97
    Compound
    0.95
     Compound
    0.94
     compound
    0.93
     Tag
    0.89
    tags
    0.84
    TAG
    0.83
    setTag
    0.82
    Activations Density 0.005%

    No Known Activations