© 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. 130273
    Prev
    Next
    INDEX
    Explanations

    letters and communications

    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
    我没有
    -2.41
    我没
    -2.17
    发布于
    -2.14
    ᡴ
    -2.08
    Ꮞ
    -2.06
     gak
    -2.05
    CurtirCurtir
    -1.98
    蕯
    -1.93
    —”
    -1.91
     anta
    -1.91
    POSITIVE LOGITS
    '
    2.44
    薮
    2.27
     crammed
    2.03
    逦
    2.02
    薷
    1.98
     seguir
    1.93
    хозяй
    1.90
    dbach
    1.85
     relieve
    1.84
    籥
    1.83
    Activations Density 0.002%

    No Known Activations