© 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. 7541
    Prev
    Next
    INDEX
    Explanations

    dash or hyphen

    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
     what
    -1.97
    所謂
    -1.67
    所谓
    -1.60
     reducing
    -1.53
     silencioso
    -1.51
     eliminating
    -1.50
     first
    -1.49
     arbeitete
    -1.48
     how
    -1.44
     schneller
    -1.41
    POSITIVE LOGITS
    籥
    1.79
    within
    1.77
    铪
    1.77
     momentous
    1.71
    丝毫
    1.62
    their
    1.59
    both
    1.57
    through
    1.50
    during
    1.50
     horrid
    1.49
    Activations Density 0.052%

    No Known Activations