© 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. 42514
    Prev
    Next
    INDEX
    Explanations

    reported speech

    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
     to
    -1.55
    ↵↵↵
    -1.51
    </h3>
    -1.49
    -1.41
     on
    -1.38
    蛧
    -1.34
    meria
    -1.28
    letion
    -1.27
    ]

    -1.25
     оригі
    -1.23
    POSITIVE LOGITS
    顺着
    1.41
    唖
    1.38
    呟
    1.36
    あっという
    1.33
     deux
    1.31
    despite
    1.29
    传来
    1.29
     the
    1.28
     dirait
    1.27
    他会
    1.27
    Activations Density 0.032%
    No Known Activations