© 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. 90189
    Prev
    Next
    INDEX
    Explanations

    fight card titles

    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
     arrivare
    -0.85
     modalità
    -0.85
    beln
    -0.84
    hecho
    -0.78
    adamente
    -0.78
    aragus
    -0.77
    kowej
    -0.76
    一緒
    -0.75
     affrontare
    -0.74
    벳
    -0.74
    POSITIVE LOGITS
    Dota
    0.87
     ferie
    0.79
    烏
    0.78
    üm
    0.77
     REDUCTION
    0.76
    atitis
    0.75
    grafie
    0.72
    ʏ
    0.72
     lengua
    0.72
    Assumptions
    0.71
    Activations Density 0.010%

    No Known Activations