© 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. 10-GEMMASCOPE-RES-131K
    7. 65554
    Prev
    Next
    INDEX
    Explanations

    years, months, days

    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_10/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
     insectes
    -1.12
     عناصر
    -1.09
    cshtml
    -1.07
    giai
    -1.07
    relatively
    -1.06
    før
    -1.05
    bbt
    -1.04
    fuß
    -1.02
     SAID
    -1.02
     Secrets
    -1.01
    POSITIVE LOGITS
     our
    1.34
     what
    1.27
     I
    1.20
     pouze
    1.20
     could
    1.16
     may
    1.15
    what
    1.14
     might
    1.13
    内に
    1.12
     it
    1.11
    Activations Density 0.228%

    No Known Activations