© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 1754
    Prev
    Next
    INDEX
    Explanations

    Rockland, CHS, Introduction

    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
    i
    -2.80
     was
    -2.64
    шая
    -2.61
     But
    -2.55
     knows
    -2.47
     from
    -2.36
    m
    -2.33
     {
    -2.13
     is
    -2.09
     seems
    -2.09
    POSITIVE LOGITS
    2
    2.77
    lgari
    2.59
    沵
    2.44
    of
    2.41
     THEIR
    2.39
    貤
    2.30
    8
    2.30
     leur
    2.27
    嗬
    2.22
    いて
    2.20
    Activations Density 0.000%

    No Known Activations