© 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. 22-GEMMASCOPE-RES-131K
    7. 68845
    Prev
    Next
    INDEX
    Explanations

    deciding needs and budget

    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_22/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
     when
    -1.15
    losti
    -1.10
    tagens
    -1.05
     mỗi
    -1.04
     by
    -1.04
     various
    -1.03
     this
    -1.02
     berbahaya
    -1.02
    に行ってきました
    -1.01
    この日は
    -0.98
    POSITIVE LOGITS
     budget
    1.20
     want
    1.14
     Tamaño
    1.13
     متوسط
    1.12
     infierno
    1.00
     for
    1.00
     démo
    0.96
     Accesorios
    0.96
     които
    0.94
     vooral
    0.94
    Activations Density 0.054%

    No Known Activations