© 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. 12706
    Prev
    Next
    INDEX
    Explanations

    detecting detriment or harm

    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_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
    Foi
    -1.54
     Volkes
    -1.45
    Ryo
    -1.44
    værende
    -1.39
    ământ
    -1.33
     Penh
    -1.32
    unków
    -1.32
    ropshire
    -1.31
    )();
    -1.30
    条目
    -1.30
    POSITIVE LOGITS
    }
    1.55
    2
    1.51
     już
    1.48
     I
    1.41
     Firstly
    1.34
    cé
    1.30
    .
    1.30
     of
    1.28
    {
    1.28
     Bedürfn
    1.26
    Activations Density 0.046%

    No Known Activations