© 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. 130919
    Prev
    Next
    INDEX
    Explanations

    "A:" followed by answer

    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
     catholique
    -1.17
    Probably
    -1.15
    ábado
    -1.13
     of
    -1.11
     so
    -1.10
    ADUATE
    -1.09
     τὸν
    -1.02
     sukker
    -1.02
     chré
    -1.01
     probably
    -1.00
    POSITIVE LOGITS
    וּ
    1.32
    ַּ
    1.25
    ּוֹ
    1.23
     Wartawan
    1.22
     raised
    1.20
    ִּ
    1.19
     proposed
    1.16
    beo
    1.09
     ExecuteAsync
    1.08
     perquè
    1.05
    Activations Density 0.009%

    No Known Activations