© 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. 19495
    Prev
    Next
    INDEX
    Explanations

    grab and acquire

    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
    ↵
    -2.38
    違う
    -2.13
     and
    -1.93
     później
    -1.81
     posteriore
    -1.73
    僂
    -1.65
    zegovina
    -1.59
    jangkau
    -1.59
    윽
    -1.59
    猻
    -1.59
    POSITIVE LOGITS
    </tfoot>
    2.45
    鍇
    2.30
    ࿆
    2.19
    泚
    2.02
    𝐒
    2.00
     }));
    1.98
     fumée
    1.94
    краси
    1.87
    </h3>
    1.84
    𞤤
    1.84
    Activations Density 0.003%

    No Known Activations