© 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. 64832
    Prev
    Next
    INDEX
    Explanations

    referring to a topic

    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
    必要があります
    -1.85
    際に
    -1.71
    為に
    -1.66
    ためには
    -1.65
    必要がある
    -1.52
    向けの
    -1.52
    際には
    -1.47
    えっ
    -1.46
    きち
    -1.40
    をしています
    -1.38
    POSITIVE LOGITS
    <bos>
    1.47
     because
    1.37
    つまり
    1.35
    饅
    1.34
    なので
    1.34
     but
    1.32
     („
    1.31
    だが
    1.30
    žiť
    1.30
    特に
    1.29
    Activations Density 0.048%

    No Known Activations