© 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. 10-GEMMASCOPE-RES-131K
    7. 119730
    Prev
    Next
    INDEX
    Explanations

    similarity or comparison operator

    np_acts-logits-general · gemini-2.5-flash-lite

    the word "like" when used to indicate similarity or comparison (as in "like-minded" or "other like devices").

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     These
    -1.88
    getLatitude
    -1.62
     ihnen
    -1.61
    </u>
    -1.61
     From
    -1.55
     große
    -1.40
    醅
    -1.40
    '],
    -1.40
    licópter
    -1.38
     eigentliche
    -1.37
    POSITIVE LOGITS
     assures
    1.53
     operações
    1.49
    '
    1.46
     boasting
    1.38
     ofrecemos
    1.37
     operação
    1.35
     partnered
    1.34
     harshly
    1.34
     piac
    1.34
    скую
    1.34
    Activations Density 0.017%

    No Known Activations