© 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. 68013
    Prev
    Next
    INDEX
    Explanations

    multiplying numbers, dates, or quotes

    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
    ἀ
    -1.04
     there
    -1.03
    ἔ
    -0.96
    新浪
    -0.94
    ないです
    -0.92
    ^{-
    -0.92
    vanje
    -0.91
    illés
    -0.91
    ApJ
    -0.90
     depois
    -0.89
    POSITIVE LOGITS
     domenica
    1.12
     äldre
    1.09
     lunedì
    1.07
     grossen
    1.05
    pheny
    1.02
    咚
    0.99
     utveckling
    0.96
    言うと
    0.96
     Nachfrage
    0.94
     onore
    0.94
    Activations Density 0.004%

    No Known Activations