© 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. 104734
    Prev
    Next
    INDEX
    Explanations

    end of code blocks

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

    closing braces or brackets in code.

    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
    蜴
    -1.41
    ordenadas
    -1.31
     męska
    -1.30
    }
    -1.26
     ạ
    -1.21
     desenli
    -1.20
    \
    -1.20
     lettres
    -1.20
     mavi
    -1.18
    (!__
    -1.17
    POSITIVE LOGITS
     these
    1.38
     the
    1.34
     belangrijke
    1.31
     which
    1.30
     each
    1.28
     this
    1.28
     atualizar
    1.24
     will
    1.23
     può
    1.23
    ')['
    1.22
    Activations Density 0.002%

    No Known Activations