© 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. 4235
    Prev
    Next
    INDEX
    Explanations

    found footage, Blumhouse, Paranormal

    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
     approving
    -0.75
    ї
    -0.72
     lunch
    -0.72
    发表
    -0.71
    jdk
    -0.71
    戌
    -0.69
     lunchtime
    -0.69
     lunches
    -0.69
    راط
    -0.68
    랙
    -0.68
    POSITIVE LOGITS
     Paran
    1.21
    found
    1.16
    Found
    1.15
     found
    1.14
     Blum
    0.98
    Cube
    0.97
     Found
    0.94
     demonic
    0.94
     gevonden
    0.93
    FOUND
    0.92
    Activations Density 0.018%

    No Known Activations