© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60053
    Prev
    Next
    INDEX
    Explanations

    consequences and conclusions

    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
    a
    -1.80
    éricos
    -1.70
    Ꮏ
    -1.65
    不仅
    -1.63
    ógicos
    -1.63
    ？」
    -1.58
    ()));
    -1.55
    '));
    -1.54
    ᎑
    -1.53
    "},
    -1.52
    POSITIVE LOGITS
    {
    2.03
     經
    1.81
    "
    1.64
    ]
    1.59
     問
    1.59
     請
    1.59
     當
    1.57
     their
    1.54
     傳
    1.51
    了不少
    1.49
    Activations Density 0.011%

    No Known Activations