© 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. 120090
    Prev
    Next
    INDEX
    Explanations

    difference in or between

    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
    鬈
    -2.59
    茀
    -2.34
     kämp
    -2.23
     karty
    -2.22
    ſtra
    -2.22
    ྃ
    -2.20
     jednej
    -2.19
    に興味
    -2.13
     difíciles
    -2.08
    珝
    -2.05
    POSITIVE LOGITS
    2
    2.94
    ).
    2.86
    d
    2.56
    3
    2.30
     know
    2.23
    </
    2.03
    and
    1.97
     between
    1.90
    </h4>
    1.89
     MUCH
    1.86
    Activations Density 0.036%

    No Known Activations