© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 1271
    Prev
    Next
    INDEX
    Explanations

    quote marks and dialogue

    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
     și
    -2.28
     и
    -2.16
     và
    -2.02
    𝖈
    -2.02
     has
    -2.00
    และ
    -1.91
    enerbah
    -1.90
     και
    -1.89
     Если
    -1.82
    拶
    -1.80
    POSITIVE LOGITS
    􀂃
    2.17
    şiv
    2.05
     inversores
    1.93
    点が
    1.92
    嫆
    1.91
    9
    1.90
    \_
    1.88
    髫
    1.87
     dekoratif
    1.86
    ſtion
    1.86
    Activations Density 0.026%

    No Known Activations