© 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. 12231
    Prev
    Next
    INDEX
    Explanations

    numbers and specific measurements

    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
    があります
    -1.63
    も
    -1.52
    と
    -1.52
    があり
    -1.48
    つまり
    -1.40
    そして
    -1.30
    を
    -1.28
    があった
    -1.21
    が
    -1.19
    がある
    -1.18
    POSITIVE LOGITS
    為に
    1.52
    ほうがいい
    1.21
    方がいい
    1.20
    際は
    1.17
    に似
    1.13
    んですが
    1.11
    ところに
    1.09
    んですよね
    1.09
    際には
    1.07
    ほうが
    1.05
    Activations Density 0.138%

    No Known Activations