© 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. 130958
    Prev
    Next
    INDEX
    Explanations

    things and existence

    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
     to
    -1.34
     will
    -1.21
    fato
    -1.17
     πρ
    -1.11
     berbeda
    -1.09
     for
    -1.09
     into
    -1.09
    Bakgrunnsstoff
    -1.07
    kében
    -1.07
     شده
    -1.06
    POSITIVE LOGITS
     everything
    1.41
     things
    1.30
     other
    1.23
     Fähigkeit
    1.20
     our
    1.17
    even
    1.16
     anything
    1.16
     every
    1.12
     brasile
    1.12
     everyone
    1.10
    Activations Density 0.057%

    No Known Activations