© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31877
    Prev
    Next
    INDEX
    Explanations

    mountain range

    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
     lowlands
    -0.90
    혁
    -0.83
     mangrove
    -0.82
    forRoot
    -0.79
    reht
    -0.76
     floodplain
    -0.76
     dandelion
    -0.76
     valley
    -0.76
     mùi
    -0.74
     embankment
    -0.74
    POSITIVE LOGITS
    ides
    1.37
     range
    1.27
     ranges
    1.14
    tops
    1.03
     Range
    1.01
    Range
    0.98
    range
    0.98
    folk
    0.92
     above
    0.91
    ranges
    0.90
    Activations Density 0.038%

    No Known Activations