© 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. 93378
    Prev
    Next
    INDEX
    Explanations

    validating input or names

    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
     ännu
    -1.03
    Джерела
    -1.00
     pēc
    -0.93
    alogie
    -0.92
     başka
    -0.91
    signol
    -0.90
    LEGO
    -0.90
    Boring
    -0.89
    спеди
    -0.89
    Bata
    -0.88
    POSITIVE LOGITS
     submitted
    1.45
    ToCheck
    1.39
     prospective
    1.27
     proposed
    1.18
     submissions
    1.08
    proposed
    1.08
     candidate
    1.06
    提交
    1.05
     submission
    1.01
     submit
    1.00
    Activations Density 0.014%

    No Known Activations