© 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. 22-GEMMASCOPE-RES-131K
    7. 39358
    Prev
    Next
    INDEX
    Explanations

    associated with

    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_22/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
     atau
    -1.41
    us
    -1.35
     You
    -1.32
    If
    -1.28
    thenburg
    -1.26
    paio
    -1.24
    閾
    -1.19
    .
    -1.19
     if
    -1.16
    çais
    -1.16
    POSITIVE LOGITS
    衚
    1.58
    盉
    1.41
     being
    1.37
     having
    1.35
    ㈭
    1.33
     nahil
    1.31
     kapture
    1.22
    鮰
    1.22
     páns
    1.22
     iſt
    1.22
    Activations Density 0.089%

    No Known Activations