© 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. 34-GEMMASCOPE-RES-131K
    4. 65361
    Prev
    Next
    INDEX
    Explanations

    describing a set

    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_34/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
    AllowAnonymous
    -0.72
     ließen
    -0.72
    āk
    -0.72
    صار
    -0.72
     pemerintahan
    -0.70
     lecz
    -0.70
     subsequently
    -0.69
     getCode
    -0.68
     EditText
    -0.68
    footnotesize
    -0.68
    POSITIVE LOGITS
     set
    4.06
     sets
    3.91
    セット
    3.58
    set
    2.92
     Sets
    2.81
     Set
    2.80
    一套
    2.64
    Set
    2.63
    ชุด
    2.58
     conjunto
    2.56
    Activations Density 0.070%

    No Known Activations