© 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. 66651
    Prev
    Next
    INDEX
    Explanations

    to infinitive verbs

    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
     ПОД
    -1.09
     něko
    -0.99
    methe
    -0.96
     on
    -0.96
    นะนำ
    -0.95
     complicaciones
    -0.95
     ПРИ
    -0.94
    čkou
    -0.93
    biker
    -0.91
    wif
    -0.91
    POSITIVE LOGITS
     their
    1.83
     its
    1.55
     свои
    1.24
    </h3>
    1.20
    ']
    1.13
    instead
    1.12
    ßen
    1.11
    作为
    1.11
    "]
    1.10
    Élet
    1.09
    Activations Density 0.078%

    No Known Activations