© 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. 65565
    Prev
    Next
    INDEX
    Explanations

    meeting specific needs

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

    This neuron is strongly triggered by the infinitive “to” when it introduces purpose- or instruction-style verbs (e.g. “to evaluate,” “to ask,” “to customize,” etc.).

    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
    ionali
    -0.94
    岗
    -0.87
    buffered
    -0.87
     Kalau
    -0.86
    👥
    -0.86
    grafi
    -0.83
    🌭
    -0.81
    Tapi
    -0.81
    //}
    -0.81
    儛
    -0.81
    POSITIVE LOGITS
     exactly
    1.48
     specific
    1.38
     what
    1.35
     requested
    1.28
     targeted
    1.24
     tailor
    1.21
     needed
    1.19
     relevant
    1.16
     according
    1.13
     requests
    1.12
    Activations Density 0.054%

    No Known Activations