© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 48540
    Prev
    Next
    INDEX
    Explanations

    know what or how

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on the word “know.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    </h3>
    -1.23
     использовании
    -1.23
     notwendigen
    -1.18
    入って
    -1.17
    ඈ
    -1.15
    amentals
    -1.15
    ोध
    -1.13
    arraycopy
    -1.13
    ),
    -1.13
    },
    -1.13
    POSITIVE LOGITS
     about
    2.69
     that
    2.05
     of
    2.05
     how
    1.84
     what
    1.42
     tujuh
    1.30
     ongeveer
    1.29
     firsthand
    1.27
     musuh
    1.18
     where
    1.15
    Activations Density 0.050%

    No Known Activations