© 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. 34-GEMMASCOPE-RES-131K
    7. 66012
    Prev
    Next
    INDEX
    Explanations

    technical methods and terms

    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_34/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
    のよう
    -1.21
    為に
    -1.18
    の時に
    -1.13
    のようです
    -1.12
    なんですね
    -1.11
    ところに
    -1.09
    をしました
    -1.08
    の絵
    -1.07
    たびに
    -1.06
    感じです
    -1.05
    POSITIVE LOGITS
    を
    2.20
    를
    1.90
    의
    1.84
    을
    1.80
    の
    1.68
    が
    1.66
    や
    1.62
    と
    1.59
    에
    1.53
     के
    1.40
    Activations Density 0.006%

    No Known Activations