© 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. 113290
    Prev
    Next
    INDEX
    Explanations

    directed to

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

    This neuron responds strongly to the occurrence of the word “directed” (and related directional prepositions like “toward” or “to”) as used in patent-style statements describing what an invention is directed to.

    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
    的血
    -1.55
     áo
    -1.51
     joy
    -1.47
    ).
    -1.42
    ępnie
    -1.41
    寕
    -1.41
    dessus
    -1.40
    minos
    -1.40
    数百
    -1.40
     love
    -1.37
    POSITIVE LOGITS
     to
    2.16
    directed
    1.59
    towards
    1.55
    ⢫
    1.52
    störungen
    1.51
     うさぎ
    1.48
    toward
    1.46
     stronę
    1.46
    さあ
    1.46
    gerichte
    1.45
    Activations Density 0.056%

    No Known Activations