© 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. 10-GEMMASCOPE-RES-131K
    7. 8984
    Prev
    Next
    INDEX
    Explanations

    aimed at

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

    This neuron detects words expressing direction toward or targeting something—especially the verb “aimed” and following preposition “at” indicating purpose.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     some
    -2.19
     more
    -2.16
    Some
    -1.81
     two
    -1.77
    ｢
    -1.75
    Even
    -1.73
     ''
    -1.72
     both
    -1.69
     less
    -1.68
    With
    -1.67
    POSITIVE LOGITS
     ранее
    1.87
     permitan
    1.58
    玙
    1.47
    镚
    1.40
    ufnahme
    1.38
     instig
    1.35
     maniere
    1.35
     is
    1.34
    蚨
    1.33
    mpion
    1.31
    Activations Density 0.066%

    No Known Activations