© 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. 103915
    Prev
    Next
    INDEX
    Explanations

    lyrics and code

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

    section headings or labels in structured documents (particularly Wikipedia-style articles).

    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
     inderdaad
    -1.68
     Our
    -1.55
    когда
    -1.54
     is
    -1.52
     olyan
    -1.45
     takiego
    -1.41
     czerwony
    -1.38
     voordeel
    -1.36
     waarschijnlijk
    -1.36
     natuurlijk
    -1.34
    POSITIVE LOGITS
     and
    1.80
     paradis
    1.63
    ́c
    1.63
     tega
    1.59
    
    1.57
     "..\..\
    1.54
     "..\..\..\
    1.53
    oció
    1.52
    .*")]
    1.50
    鹩
    1.48
    Activations Density 0.040%

    No Known Activations