© 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. 33178
    Prev
    Next
    INDEX
    Explanations

    film titles and release year

    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
     olvas
    -1.05
    Rptr
    -1.05
     indietro
    -1.04
     firent
    -1.00
     giù
    -0.93
    '):
    -0.93
    ))(
    -0.92
     Senhora
    -0.91
    trecht
    -0.91
     chré
    -0.91
    POSITIVE LOGITS
    released
    1.04
     صدر
    1.00
     released
    0.98
     Released
    0.97
     film
    0.94
    Released
    0.92
     adaptation
    0.91
     AppCompatTheme
    0.88
     Directed
    0.88
    adaptation
    0.87
    Activations Density 0.037%

    No Known Activations