© 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. 119549
    Prev
    Next
    INDEX
    Explanations

    Christopher followed by names

    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
    er
    -2.09
    "
    -2.06
    or
    -1.91
    瓩
    -1.91
     defi
    -1.88
    lo
    -1.87
    \
    -1.84
     permettra
    -1.83
    ｏ
    -1.83
    $
    -1.82
    POSITIVE LOGITS
     estekak
    2.20
     Which
    2.19
    霂
    2.14
    枓
    2.13
     Then
    2.08
    这里
    2.05
    缥
    2.03
     voidaan
    2.00
     ")";
    1.99
     欣赏
    1.98
    Activations Density 0.010%

    No Known Activations