© 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. 34-GEMMASCOPE-RES-131K
    7. 86811
    Prev
    Next
    INDEX
    Explanations

    GNU GPL license texts

    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
    AMPTON
    -0.80
    三
    -0.71
     doorbell
    -0.71
    非
    -0.66
    zczy
    -0.63
     thighs
    -0.62
    还
    -0.62
    촌
    -0.62
    Mhm
    -0.62
     rep
    -0.62
    POSITIVE LOGITS
    Sia
    0.77
     Gracie
    0.76
     márm
    0.74
     tè
    0.74
     sleeping
    0.71
     banged
    0.70
     FACILITY
    0.70
     justiça
    0.69
     Pile
    0.69
    ILS
    0.68
    Activations Density 0.111%

    No Known Activations