© 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. 57403
    Prev
    Next
    INDEX
    Explanations

    plus symbol conjunction

    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
     dostępne
    -1.99
    ねえ
    -1.84
     cornerstone
    -1.78
    当时的
    -1.77
    なんですが
    -1.76
     kebiasaan
    -1.76
     you
    -1.74
     mengumumkan
    -1.74
     Что
    -1.72
     Despite
    -1.69
    POSITIVE LOGITS
     of
    2.17
    },
    2.02
    潆
    1.92
    ⭓
    1.86
    糅
    1.85
    which
    1.84
    鬟
    1.82
     also
    1.82
    之色
    1.79
    resizingMask
    1.77
    Activations Density 0.036%

    No Known Activations