© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15097
    Prev
    Next
    INDEX
    Explanations

    pairs and multiples

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

    The neuron activates strongly on individual capitalized name tokens (people’s proper names).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     and
    -1.40
     or
    -1.22
     for
    -1.21
     out
    -1.14
     relevant
    -1.13
     change
    -1.12
     if
    -1.11
     C
    -1.09
     provided
    -1.09
     R
    -1.07
    POSITIVE LOGITS
     themselves
    1.69
     duo
    1.53
     Mereka
    1.46
     jejich
    1.39
     brothers
    1.39
    duo
    1.38
    他们是
    1.30
    THEY
    1.28
     their
    1.27
    jährigen
    1.24
    Activations Density 0.054%

    No Known Activations