© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12514
    Prev
    Next
    INDEX
    Explanations

    positional descriptions

    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
    がある
    -1.45
    に対する
    -1.43
    があり
    -1.43
    なども
    -1.35
    <bos>
    -1.32
    ですが
    -1.30
    つまり
    -1.29
    と思いました
    -1.27
    もちろん
    -1.24
    における
    -1.22
    POSITIVE LOGITS
     and
    1.88
    ditionally
    1.35
     one
    1.32
    romas
    1.28
    んですよ
    1.27
     azt
    1.27
    RTLU
    1.25
     toalla
    1.25
    明日は
    1.23
     cintas
    1.23
    Activations Density 0.103%

    No Known Activations