© 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. 66572
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and symbols

    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
     There
    -1.85
     are
    -1.76
     there
    -1.58
     includes
    -1.45
     create
    -1.41
     include
    -1.41
     including
    -1.40
    There
    -1.36
     November
    -1.34
     At
    -1.32
    POSITIVE LOGITS
    entially
    1.62
     istr
    1.60
    lograph
    1.59
    igth
    1.59
     花纹
    1.58
     conflic
    1.58
    licopter
    1.53
    ޏ
    1.52
     desn
    1.52
    brtc
    1.51
    Activations Density 0.079%

    No Known Activations