© 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. 1212
    Prev
    Next
    INDEX
    Explanations

    missile systems

    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
    ();
    -2.58
    ।
    -2.50
     awkwardly
    -2.42
     succumb
    -2.31
    ྅
    -2.30
     effortlessly
    -2.28
     Saltar
    -2.28
     einer
    -2.27
    </sup>
    -2.20
    </tr>
    -2.19
    POSITIVE LOGITS
    </i>
    2.75
    isation
    2.56
     conhecida
    2.55
    ка
    2.48
    齪
    2.39
     llegan
    2.33
    鴬
    2.33
    鞮
    2.30
     destes
    2.23
     häufigsten
    2.23
    Activations Density 0.002%

    No Known Activations