© 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. 71442
    Prev
    Next
    INDEX
    Explanations

    quantities per unit

    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
    があり
    -2.64
    などを
    -2.63
    などが
    -2.56
    と
    -2.50
    つまり
    -2.28
    や
    -2.25
    そして
    -2.14
    などは
    -2.13
    などの
    -2.08
    もある
    -2.08
    POSITIVE LOGITS
    為に
    3.06
    久し
    2.84
    んですよ
    2.64
    んですよね
    2.58
    気がします
    2.55
    明日は
    2.53
    ほら
    2.48
    もうすぐ
    2.44
    ところに
    2.44
    ＝＝＝＝
    2.41
    Activations Density 0.016%

    No Known Activations