© 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. 10-GEMMASCOPE-RES-131K
    7. 119973
    Prev
    Next
    INDEX
    Explanations

    movie or film

    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_10/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
    encji
    -1.68
    </sup>
    -1.59
     parezca
    -1.46
    ıyoruz
    -1.42
    cinoma
    -1.41
    UTTON
    -1.40
     explot
    -1.38
    ꪔ
    -1.38
    ässä
    -1.38
    jabat
    -1.37
    POSITIVE LOGITS
     to
    2.42
     that
    2.25
     gesprochen
    1.71
    er
    1.60
    </h3>
    1.55
    _
    1.55
     vorgestellt
    1.50
     möglicherweise
    1.48
     verstanden
    1.47
    adering
    1.46
    Activations Density 0.055%

    No Known Activations