© 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. 130431
    Prev
    Next
    INDEX
    Explanations

    `<ul>` and `<li>` HTML tags

    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
    Regardless
    -1.95
     stället
    -1.91
     But
    -1.87
    Although
    -1.86
    Since
    -1.77
    贗
    -1.74
    Despite
    -1.73
     vissa
    -1.69
    进行了
    -1.67
     Atención
    -1.67
    POSITIVE LOGITS
    }$.
    2.36
    凩
    2.14
    }$,
    2.08
    ᕮ
    1.99
    卧槽
    1.91
    𓆜
    1.88
    嫫
    1.84
    嗩
    1.78
    ;?
    1.77
    €¦
    1.73
    Activations Density 0.003%

    No Known Activations