© 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. 35834
    Prev
    Next
    INDEX
    Explanations

    your needs and wants

    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
     памя
    -1.02
    luia
    -0.99
     掃除
    -0.96
    frau
    -0.96
     apropri
    -0.94
    patreon
    -0.93
     never
    -0.92
     говорится
    -0.92
     corect
    -0.91
    лару
    -0.91
    POSITIVE LOGITS
     your
    2.06
     you
    1.82
     needs
    1.77
     cần
    1.52
     chcesz
    1.29
     potrzebu
    1.27
     nécessite
    1.23
     potrze
    1.20
     wants
    1.19
     needing
    1.17
    Activations Density 0.036%

    No Known Activations