© 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. 1677
    Prev
    Next
    INDEX
    Explanations

    agency responsible for

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

    The neuron fires on the key noun in Wikipedia‐style definition sentences (e.g. “agency,” “department,” “division,” “board,” “cells,” etc.) — the head noun of “X is a Y” introductions.

    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
    ječ
    -0.83
    とろ
    -0.81
    atsen
    -0.81
    vident
    -0.80
    contain
    -0.78
    úš
    -0.77
    gypte
    -0.77
    Surviving
    -0.75
     contiene
    -0.74
    مدیر
    -0.74
    POSITIVE LOGITS
     responsible
    5.31
     tasked
    4.38
    responsible
    4.06
    Responsible
    3.25
     Responsible
    3.19
     responsibility
    3.14
     responsável
    3.08
    负责
    3.02
     responsable
    2.77
     encargado
    2.75
    Activations Density 0.134%

    No Known Activations