© 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. 34-GEMMASCOPE-RES-131K
    7. 47624
    Prev
    Next
    INDEX
    Explanations

    similarly, equally, correspondingly

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

    The neuron strongly responds to phrases expressing unfortunate timing or location—most notably “in the wrong place at the wrong time.”

    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
    starred
    -0.93
    ِّ
    -0.91
     soient
    -0.90
    mao
    -0.86
     Estrella
    -0.85
    romatic
    -0.84
    aid
    -0.83
    uro
    -0.82
    вшего
    -0.82
    faster
    -0.82
    POSITIVE LOGITS
     equally
    1.85
     altrett
    1.65
     correspondingly
    1.55
     Equally
    1.34
     Könige
    1.16
     Similarly
    1.16
     Brasilien
    1.06
     similarly
    1.05
     Likewise
    1.02
     equivalently
    1.02
    Activations Density 0.194%

    No Known Activations