© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 65253
    Prev
    Next
    INDEX
    Explanations

    actions of altering or fixing

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

    The neuron strongly activates on past‐tense action verbs (verbs ending in “-ed”).

    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
    齣
    -1.38
    dicionado
    -1.25
     you
    -1.24
     its
    -1.17
    Its
    -1.08
    这种
    -1.06
     вашего
    -1.05
     имел
    -1.04
     данного
    -1.04
     großes
    -1.04
    POSITIVE LOGITS
     the
    2.72
     it
    1.99
     them
    1.63
     everything
    1.54
     things
    1.25
    ibilità
    1.25
    everything
    1.20
     him
    1.19
     wszyst
    1.13
     één
    1.12
    Activations Density 0.104%

    No Known Activations