© 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. 109031
    Prev
    Next
    INDEX
    Explanations

    distinctive characteristics

    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
     greater
    -0.96
     wholly
    -0.87
     give
    -0.84
    饅
    -0.84
     Erweiter
    -0.82
     generally
    -0.82
     totally
    -0.82
     pursue
    -0.82
    ;'>
    -0.82
    tecs
    -0.82
    POSITIVE LOGITS
     Ministre
    1.13
     consac
    1.09
    ⌊
    0.94
     hadde
    0.90
     Gouvernement
    0.89
     nommée
    0.88
     hossz
    0.87
     créée
    0.87
     hatte
    0.85
     gehört
    0.85
    Activations Density 0.018%

    No Known Activations