© 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. 67500
    Prev
    Next
    INDEX
    Explanations

    mortgage sale, license, company, statistics, appeals

    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
     and
    -1.76
    づけ
    -1.70
    様な
    -1.66
    為に
    -1.66
    ところに
    -1.66
    ślę
    -1.56
    $\%$
    -1.49
    N
    -1.49
     A
    -1.47
    ほら
    -1.46
    POSITIVE LOGITS
    がありますが
    2.59
    <bos>
    2.30
    もしか
    2.02
    は
    1.99
    醍
    1.95
    があります
    1.94
    や
    1.92
    を
    1.84
    がある
    1.84
     作り方
    1.82
    Activations Density 0.132%

    No Known Activations