© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 117990
    Prev
    Next
    INDEX
    Explanations

    Scranton Wilkes-Barre Pennsylvania

    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
     realtà
    -0.85
     convolutional
    -0.83
     infection
    -0.81
     wheat
    -0.81
    ætte
    -0.80
    [['
    -0.78
     остро
    -0.77
     wirken
    -0.77
     Crouch
    -0.76
    ប
    -0.74
    POSITIVE LOGITS
     Scranton
    1.30
     Wilkes
    1.22
    Barre
    0.96
    Wyoming
    0.91
     Miners
    0.88
     Wyoming
    0.86
     LUZ
    0.85
    Miser
    0.82
    Lom
    0.79
    洄
    0.79
    Activations Density 0.026%

    No Known Activations