© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73126
    Prev
    Next
    INDEX
    Explanations

    not only ... but also

    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
    や
    -2.09
    を
    -2.06
    があります
    -1.79
    が
    -1.79
    は
    -1.76
    も
    -1.74
    と
    -1.64
    だが
    -1.57
    <bos>
    -1.57
    がある
    -1.51
    POSITIVE LOGITS
    為に
    1.74
    様な
    1.70
    ようになります
    1.62
    明日は
    1.61
    になったら
    1.54
    の方に
    1.49
    久し
    1.48
    際には
    1.47
    に戻る
    1.46
    来週
    1.45
    Activations Density 0.019%

    No Known Activations