© 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. 3691
    Prev
    Next
    INDEX
    Explanations

    page number, line number, sequence number

    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
     There
    -2.64
     If
    -2.38
    </h4>
    -2.30
     While
    -2.16
     them
    -2.16
     They
    -2.06
     At
    -2.00
     Although
    -1.98
     by
    -1.90
    ).
    -1.90
    POSITIVE LOGITS
     trám
    2.22
    厹
    2.17
    CurtirCurtir
    1.99
     indiví
    1.91
     incrí
    1.88
    ⵈ
    1.84
    Takk
    1.83
    ᷆
    1.83
     münchen
    1.82
    蛱
    1.82
    Activations Density 0.018%

    No Known Activations