© 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. 119567
    Prev
    Next
    INDEX
    Explanations

    cinnamon, Hindu karma, selectAll

    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
    y
    -3.08
    ﮏ
    -2.69
    ⸒
    -2.66
    ?’
    -2.56
     selben
    -2.55
    </em>
    -2.55
    敉
    -2.50
    ⡯
    -2.48
    荩
    -2.44
    🦣
    -2.42
    POSITIVE LOGITS
    狆
    3.09
    蠵
    2.92
    I
    2.63
    特别的
    2.61
    
    2.58
    憮
    2.56
     termed
    2.55
     were
    2.55
    镚
    2.44
    ۹
    2.42
    Activations Density 0.011%

    No Known Activations