© 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. 10-GEMMASCOPE-RES-131K
    4. 105397
    Prev
    Next
    INDEX
    Explanations

    detecting similarity

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

    the phrase "similar to" followed by a noun or noun phrase.

    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
    
    -1.99
    骜
    -1.88
    paramInt
    -1.86
     impos
    -1.84
    ()]
    
    -1.82
    на
    -1.81
    derdag
    -1.80
    >());
    -1.77
    ulipas
    -1.77
     "--
    -1.75
    POSITIVE LOGITS
    }
    2.23
    専用の
    2.05
     other
    1.97
     that
    1.95
    estaba
    1.88
     armados
    1.84
     aplicado
    1.83
     others
    1.81
     débit
    1.81
     those
    1.78
    Activations Density 0.021%

    No Known Activations