© 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. 93177
    Prev
    Next
    INDEX
    Explanations

    titles, ranks, and professions

    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
     anunció
    -1.41
     mengumumkan
    -1.33
     çünkü
    -1.22
     confirmó
    -1.20
    Dữ
    -1.20
     suuri
    -1.16
     any
    -1.13
    ṝ
    -1.12
     Botox
    -1.11
     lantaran
    -1.09
    POSITIVE LOGITS
     inalámb
    1.19
    ]='\
    1.19
     địch
    1.18
    tagens
    1.17
     including
    1.16
    ntilde
    1.16
     during
    1.12
     workers
    1.11
    教材
    1.10
     wood
    1.09
    Activations Density 0.021%

    No Known Activations