© 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. 12881
    Prev
    Next
    INDEX
    Explanations

    ISBN numbers and publishers

    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
    🡺
    -1.80
    ⭓
    -1.72
    ⬈
    -1.67
    を引
    -1.66
    </h5>
    -1.63
    ons
    -1.63
    憷
    -1.57
    ar
    -1.55
     renowned
    -1.52
    ol
    -1.51
    POSITIVE LOGITS
    Shortly
    1.74
    Since
    1.59
     their
    1.59
    During
    1.58
    After
    1.44
    ༊
    1.43
    Despite
    1.41
    Both
    1.40
    ⦑
    1.38
     Они
    1.35
    Activations Density 0.001%

    No Known Activations