© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113046
    Prev
    Next
    INDEX
    Explanations

    ling, linger, lingual

    np_acts-logits-general · gemini-2.5-flash-lite

    the presence of the character sequence “ling” inside a token.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    釹
    -2.47
    椟
    -2.42
     seperti
    -2.31
    猻
    -2.27
    ↵
    -2.22
    袮
    -2.19
    feinander
    -2.16
    崃
    -2.16
     mereka
    -2.14
     colère
    -2.14
    POSITIVE LOGITS
    ]
    4.03
    }
    3.55
    {
    3.36
    ).
    3.25
    </h2>
    2.56
    `
    2.36
    纔
    2.30
    なんだろう
    2.28
    ра
    2.27
    没有
    2.27
    Activations Density 0.006%

    No Known Activations