© 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. 603
    Prev
    Next
    INDEX
    Explanations

    scientific classification or non-English terms

    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
     following
    -0.84
    andang
    -0.83
     звука
    -0.80
    UM
    -0.79
    ica
    -0.79
     Wohnungen
    -0.79
    нению
    -0.77
     Henry
    -0.77
     Sha
    -0.77
    中略
    -0.76
    POSITIVE LOGITS
    ↵↵↵↵↵
    1.09
    ↵↵↵
    1.05
    ↵↵↵↵
    0.96
    альная
    0.92
    Ƚ
    0.90
    ↵↵↵↵↵↵↵
    0.90
     неиз
    0.90
    ↵↵↵↵↵↵
    0.88
    deutung
    0.86
     BRAD
    0.85
    Activations Density 0.016%

    No Known Activations