© 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. 44953
    Prev
    Next
    INDEX
    Explanations

    reporting 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
    </h1>
    -2.33
    和
    -1.70
    le
    -1.70
    ↵↵
    -1.61
    ными
    -1.58
     saludables
    -1.58
    に
    -1.56
     it
    -1.56
     what
    -1.55
     In
    -1.53
    POSITIVE LOGITS
    ᯅ
    2.09
    寕
    2.05
    ⑊
    2.00
    ꪻ
    1.98
     parachoque
    1.94
    錞
    1.94
    Compared
    1.91
    を作り
    1.89
     水彩
    1.89
    を買う
    1.87
    Activations Density 0.002%

    No Known Activations